embodied ai - 2025_10
Navigation
Home / Papers / embodied ai
- Part 1
- Part 2
Papers
Assembly Theory (AT) and its central measure, the assembly index (Ai), represent an invaluable opportunity to address some of the most persistent and widespread conflations and misconceptions about computability and complexity theory in science. The AT defence embodies several common concurrent misconceptions that pile on each other: the belief that Turing machines impose artefactual constraints, the mischaracterisation of Kolmogorov complexity as inapplicable, and the claims around Ai as different from Shannon entropy or compression algorithms. Here we show that the new arguments advanced by the AT group in their defence, are based on misleading and incomplete experiments that, when completed, show the extent of the correlations and overlapping with popular statistical compression algorithms, conforming with the mathematical equivalence to Shannon entropy previously mathematically proved and reported, which remains undisputed. Through theoretical and empirical analysis, we show that Ai does not offer a path towards fundamental novel causal or informational insights beyond what existing statistical frameworks already offer. Rather than offering a unifying theory of life as the AT authors suggest, we argue that AT obfuscates the field and provides a cautionary example of how the accumulation of conceptual mistakes can lead to a misleading theory. Finally, we show that Ai is a particular limited case of another complexity metric based on algorithmic (Kolmogorov) complexity, consisting of decomposing an object into its causal blocks that goes beyond, and outperforms, AT.
Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language models (VLMs) excel at perception tasks but struggle with fine-grained spatial reasoning due to their implicit, correlation-driven reasoning and reliance solely on images. We propose a novel neuro_symbolic framework that integrates both panoramic-image and 3D point cloud information, combining neural perception with symbolic reasoning to explicitly model spatial and logical relationships. Our framework consists of a perception module for detecting entities and extracting attributes, and a reasoning module that constructs a structured scene graph to support precise, interpretable queries. Evaluated on the JRDB-Reasoning dataset, our approach demonstrates superior performance and reliability in crowded, human_built environments while maintaining a lightweight design suitable for robotics and embodied AI applications.
We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations into structured robot states-such as 3D keypoints or joint angles-from a single RGB image, eliminating the need for multi-stage pipelines or auxiliary modalities. Building upon this foundation, PoseDiff extends naturally to video-to-action inverse dynamics: by conditioning on sparse video keyframes generated by world models, it produces smooth and continuous long-horizon action sequences through an overlap-averaging strategy. This unified design enables scalable and efficient integration of perception and control. On the DREAM dataset, PoseDiff achieves state-of-the-art accuracy and real-time performance for pose estimation. On Libero-Object manipulation tasks, it substantially improves success rates over existing inverse dynamics modules, even under strict offline settings. Together, these results show that PoseDiff provides a scalable, accurate, and efficient bridge between perception, planning, and control in embodied AI. The video visualization results can be found on the project page: https://haozhuo-zhang.github.io/PoseDiff-project-page/.
Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language models (VLMs) excel at perception tasks but struggle with fine-grained spatial reasoning due to their implicit, correlation-driven reasoning and reliance solely on images. We propose a novel neuro_symbolic framework that integrates both panoramic-image and 3D point cloud information, combining neural perception with symbolic reasoning to explicitly model spatial and logical relationships. Our framework consists of a perception module for detecting entities and extracting attributes, and a reasoning module that constructs a structured scene graph to support precise, interpretable queries. Evaluated on the JRDB-Reasoning dataset, our approach demonstrates superior performance and reliability in crowded, human_built environments while maintaining a lightweight design suitable for robotics and embodied AI applications.
Current advances in AI and its applicability have highlighted the need to ensure its trustworthiness for legal, ethical, and even commercial reasons. Sub-symbolic machine learning algorithms, such as the LLMs, simulate reasoning but hallucinate and their decisions cannot be explained or audited (crucial aspects for trustworthiness). On the other hand, rule-based reasoners, such as Cyc, are able to provide the chain of reasoning steps but are complex and use a large number of reasoners. We propose a middle ground using s(CASP), a goal-directed constraint-based answer set programming reasoner that employs a small number of mechanisms to emulate reliable and explainable human-style commonsense reasoning. In this paper, we explain how s(CASP) supports the 16 desiderata for trustworthy AI introduced by Doug Lenat and Gary Marcus (2023), and two additional ones: inconsistency detection and the assumption of alternative worlds. To illustrate the feasibility and synergies of s(CASP), we present a range of diverse applications, including a conversational chatbot and a virtually embodied reasoner.
This report presents Pelican-VL 1.0, a new family of open-source embodied brain models with parameter scales ranging from 7 billion to 72 billion. Our explicit mission is clearly stated as: To embed powerful intelligence into various embodiments. Pelican-VL 1.0 is currently the largest-scale open-source embodied multimodal brain model. Its core advantage lies in the in-depth integration of data power and intelligent adaptive learning mechanisms. Specifically, metaloop distilled a high-quality dataset from a raw dataset containing 4+ billion tokens. Pelican-VL 1.0 is trained on a large-scale cluster of 1000+ A800 GPUs, consuming over 50k+ A800 GPU-hours per checkpoint. This translates to a 20.3% performance uplift from its base model and outperforms 100B-level open-source counterparts by 10.6%, placing it on par with leading proprietary systems on well-known embodied benchmarks. We establish a novel framework, DPPO (Deliberate Practice Policy Optimization), inspired by human metacognition to train Pelican-VL 1.0. We operationalize this as a metaloop that teaches the AI to practice deliberately, which is a RL-Refine-Diagnose-SFT loop.
We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework. At its core, PoseDiff maps raw visual observations into structured robot states-such as 3D keypoints or joint angles-from a single RGB image, eliminating the need for multi-stage pipelines or auxiliary modalities. Building upon this foundation, PoseDiff extends naturally to video-to-action inverse dynamics: by conditioning on sparse video keyframes generated by world models, it produces smooth and continuous long-horizon action sequences through an overlap-averaging strategy. This unified design enables scalable and efficient integration of perception and control. On the DREAM dataset, PoseDiff achieves state-of-the-art accuracy and real-time performance for pose estimation. On Libero-Object manipulation tasks, it substantially improves success rates over existing inverse dynamics modules, even under strict offline settings. Together, these results show that PoseDiff provides a scalable, accurate, and efficient bridge between perception, planning, and control in embodied AI. The video visualization results can be found on the project page: https://haozhuo-zhang.github.io/PoseDiff-project-page/.
Large language models (LLMs) are increasingly shaping creative work and problem-solving; however, prior research suggests that they may diminish unassisted creativity. To address this tension, a coach-like LLM environment was developed that embodies divergent and convergent thinking personas as two complementary processes. Effectiveness and user behavior were assessed through a controlled experiment in which participants interacted with either persona, while a control group engaged with a standard LLM providing direct answers. Notably, users' perceptions of which persona best supported their creativity often diverged from objective performance measures. Trait-based analyses revealed that individual differences predict when people utilize divergent versus convergent personas, suggesting opportunities for adaptive sequencing. Furthermore, interaction patterns reflected the design thinking model, demonstrating how persona-guided support shapes creative problem-solving. Our findings provide design principles for creativity support systems that strike a balance between exploration and convergence through persona-based guidance and personalization. These insights advance human-AI collaboration tools that scaffold rather than overshadow human creativity.
Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing promising performance across diverse spatial tasks. However, systematic reviews and publicly available benchmarks for these models remain limited. In this survey, we provide a comprehensive review of multimodal spatial reasoning tasks with large models, categorizing recent progress in multimodal large language models (MLLMs) and introducing open benchmarks for evaluation. We begin by outlining general spatial reasoning, focusing on post-training techniques, explainability, and architecture. Beyond classical 2D tasks, we examine spatial relationship reasoning, scene and layout understanding, as well as visual question answering and grounding in 3D space. We also review advances in embodied AI, including vision-language navigation and action models. Additionally, we consider emerging modalities such as audio and egocentric video, which contribute to novel spatial understanding through new sensors. We believe this survey establishes a solid foundation and offers insights into the growing field of multimodal spatial reasoning. Updated information about this survey, codes and implementation of the open benchmarks can be found at https://github.com/zhengxuJosh/Awesome-Spatial-Reasoning.
Generating hand grasps with language instructions is a widely studied topic that benefits from embodied AI and VR/AR applications. While transferring into hand articulatied object interaction (HAOI), the hand grasps synthesis requires not only object functionality but also long-term manipulation sequence along the object deformation. This paper proposes a novel HAOI sequence generation framework SynHLMA, to synthesize hand language manipulation for articulated objects. Given a complete point cloud of an articulated object, we utilize a discrete HAOI representation to model each hand object interaction frame. Along with the natural language embeddings, the representations are trained by an HAOI manipulation language model to align the grasping process with its language description in a shared representation space. A joint-aware loss is employed to ensure hand grasps follow the dynamic variations of articulated object joints. In this way, our SynHLMA achieves three typical hand manipulation tasks for articulated objects of HAOI generation, HAOI prediction and HAOI interpolation. We evaluate SynHLMA on our built HAOI-lang dataset and experimental results demonstrate the superior hand grasp sequence generation performance comparing with state-of-the-art. We also show a robotics grasp application that enables dexterous grasps execution from imitation learning using the manipulation sequence provided by our SynHLMA. Our codes and datasets will be made publicly available.
The rapid advancement of Large Language Models (LLMs) has marked a significant breakthrough in Artificial Intelligence (AI), ushering in a new era of Human-centered Artificial Intelligence (HAI). HAI aims to better serve human welfare and needs, thereby placing higher demands on the intelligence level of robots, particularly in aspects such as natural language interaction, complex task planning, and execution. Intelligent agents powered by LLMs have opened up new pathways for realizing HAI. However, existing LLM-based embodied agents often lack the ability to plan and execute complex natural language control tasks online. This paper explores the implementation of intelligent robotic manipulating agents based on Vision-Language Models (VLMs) in the physical world. We propose a novel embodied agent framework for robots, which comprises a human-robot voice interaction module, a vision-language agent module and an action execution module. The vision-language agent itself includes a vision-based task planner, a natural language instruction converter, and a task performance feedback evaluator. Experimental results demonstrate that our agent achieves a 28\% higher average task success rate in both simulated and real environments compared to approaches relying solely on LLM+CLIP, significantly improving the execution success rate of high-level natural language instruction tasks.
Generating hand grasps with language instructions is a widely studied topic that benefits from embodied AI and VR/AR applications. While transferring into hand articulatied object interaction (HAOI), the hand grasps synthesis requires not only object functionality but also long-term manipulation sequence along the object deformation. This paper proposes a novel HAOI sequence generation framework SynHLMA, to synthesize hand language manipulation for articulated objects. Given a complete point cloud of an articulated object, we utilize a discrete HAOI representation to model each hand object interaction frame. Along with the natural language embeddings, the representations are trained by an HAOI manipulation language model to align the grasping process with its language description in a shared representation space. A joint-aware loss is employed to ensure hand grasps follow the dynamic variations of articulated object joints. In this way, our SynHLMA achieves three typical hand manipulation tasks for articulated objects of HAOI generation, HAOI prediction and HAOI interpolation. We evaluate SynHLMA on our built HAOI-lang dataset and experimental results demonstrate the superior hand grasp sequence generation performance comparing with state-of-the-art. We also show a robotics grasp application that enables dexterous grasps execution from imitation learning using the manipulation sequence provided by our SynHLMA. Our codes and datasets will be made publicly available.
The rapid advancement of Large Language Models (LLMs) has marked a significant breakthrough in Artificial Intelligence (AI), ushering in a new era of Human-centered Artificial Intelligence (HAI). HAI aims to better serve human welfare and needs, thereby placing higher demands on the intelligence level of robots, particularly in aspects such as natural language interaction, complex task planning, and execution. Intelligent agents powered by LLMs have opened up new pathways for realizing HAI. However, existing LLM-based embodied agents often lack the ability to plan and execute complex natural language control tasks online. This paper explores the implementation of intelligent robotic manipulating agents based on Vision-Language Models (VLMs) in the physical world. We propose a novel embodied agent framework for robots, which comprises a human-robot voice interaction module, a vision-language agent module and an action execution module. The vision-language agent itself includes a vision-based task planner, a natural language instruction converter, and a task performance feedback evaluator. Experimental results demonstrate that our agent achieves a 28\% higher average task success rate in both simulated and real environments compared to approaches relying solely on LLM+CLIP, significantly improving the execution success rate of high-level natural language instruction tasks.
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have advanced visual fidelity, they often remain constrained to fixed scene categories, lack sufficient object-level detail and physical consistency, and struggle to align with complex user instructions. In this work, we present SceneWeaver, a reflective agentic framework that unifies diverse scene synthesis paradigms through tool-based iterative refinement. At its core, SceneWeaver employs a language model-based planner to select from a suite of extensible scene generation tools, ranging from data-driven generative models to visual- and LLM-based methods, guided by self-evaluation of physical plausibility, visual realism, and semantic alignment with user input. This closed-loop reason-act-reflect design enables the agent to identify semantic inconsistencies, invoke targeted tools, and update the environment over successive iterations. Extensive experiments on both common and open-vocabulary room types demonstrate that SceneWeaver not only outperforms prior methods on physical, visual, and semantic metrics, but also generalizes effectively to complex scenes with diverse instructions, marking a step toward general-purpose 3D environment generation. Project website: https://scene-weaver.github.io/.
The rapid evolution of agentic AI marks a new phase in artificial intelligence, where Large Language Models (LLMs) no longer merely respond but act, reason, and adapt. This survey traces the paradigm shift in building agentic AI: from Pipeline-based systems, where planning, tool use, and memory are orchestrated by external logic, to the emerging Model-native paradigm, where these capabilities are internalized within the model's parameters. We first position Reinforcement Learning (RL) as the algorithmic engine enabling this paradigm shift. By reframing learning from imitating static data to outcome-driven exploration, RL underpins a unified solution of LLM + RL + Task across language, vision and embodied domains. Building on this, the survey systematically reviews how each capability -- Planning, Tool use, and Memory -- has evolved from externally scripted modules to end-to-end learned behaviors. Furthermore, it examines how this paradigm shift has reshaped major agent applications, specifically the Deep Research agent emphasizing long-horizon reasoning and the GUI agent emphasizing embodied interaction. We conclude by discussing the continued internalization of agentic capabilities like Multi-agent collaboration and Reflection, alongside the evolving roles of the system and model layers in future agentic AI. Together, these developments outline a coherent trajectory toward model-native agentic AI as an integrated learning and interaction framework, marking the transition from constructing systems that apply intelligence to developing models that grow intelligence through experience.
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have advanced visual fidelity, they often remain constrained to fixed scene categories, lack sufficient object-level detail and physical consistency, and struggle to align with complex user instructions. In this work, we present SceneWeaver, a reflective agentic framework that unifies diverse scene synthesis paradigms through tool-based iterative refinement. At its core, SceneWeaver employs a language model-based planner to select from a suite of extensible scene generation tools, ranging from data-driven generative models to visual- and LLM-based methods, guided by self-evaluation of physical plausibility, visual realism, and semantic alignment with user input. This closed-loop reason-act-reflect design enables the agent to identify semantic inconsistencies, invoke targeted tools, and update the environment over successive iterations. Extensive experiments on both common and open-vocabulary room types demonstrate that SceneWeaver not only outperforms prior methods on physical, visual, and semantic metrics, but also generalizes effectively to complex scenes with diverse instructions, marking a step toward general-purpose 3D environment generation. Project website: https://scene-weaver.github.io/.
Aligning robot behavior with human preferences is crucial for deploying embodied AI agents in human-centered environments. A promising solution is interactive imitation learning from human intervention, where a human expert observes the policy's execution and provides interventions as feedback. However, existing methods often fail to utilize the prior policy efficiently to facilitate learning, thus hindering sample efficiency. In this work, we introduce MEReQ (Maximum-Entropy Residual-Q Inverse Reinforcement Learning), designed for sample-efficient alignment from human intervention. Instead of inferring the complete human behavior characteristics, MEReQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions. It then employs Residual Q-Learning (RQL) to align the policy with human preferences using this residual reward function. Extensive evaluations on simulated and real-world tasks demonstrate that MEReQ achieves sample-efficient policy alignment from human intervention.
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video generation, many of their inference strategies have been directly transferred to control domains without adaptation. In this work, we show that by tailoring the denoising process to the specific characteristics of embodied AI tasks -- particularly structured, low-dimensional nature of action distributions -- diffusion policies can operate effectively with as few as 5 neural function evaluations (NFE). Building on this insight, we propose a population-based sampling strategy, genetic denoising, which enhances both performance and stability by selecting denoising trajectories with low out-of-distribution risk. Our method solves challenging tasks with only 2 NFE while improving or matching performance. We evaluate our approach across 14 robotic manipulation tasks from D4RL and Robomimic, spanning multiple action horizons and inference budgets. In over 2 million evaluations, our method consistently outperforms standard diffusion-based policies, achieving up to 20\% performance gains with significantly fewer inference steps.
Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video generation, many of their inference strategies have been directly transferred to control domains without adaptation. In this work, we show that by tailoring the denoising process to the specific characteristics of embodied AI tasks -- particularly structured, low-dimensional nature of action distributions -- diffusion policies can operate effectively with as few as 5 neural function evaluations (NFE). Building on this insight, we propose a population-based sampling strategy, genetic denoising, which enhances both performance and stability by selecting denoising trajectories with low out-of-distribution risk. Our method solves challenging tasks with only 2 NFE while improving or matching performance. We evaluate our approach across 14 robotic manipulation tasks from D4RL and Robomimic, spanning multiple action horizons and inference budgets. In over 2 million evaluations, our method consistently outperforms standard diffusion-based policies, achieving up to 20\% performance gains with significantly fewer inference steps.
Aligning robot behavior with human preferences is crucial for deploying embodied AI agents in human-centered environments. A promising solution is interactive imitation learning from human intervention, where a human expert observes the policy's execution and provides interventions as feedback. However, existing methods often fail to utilize the prior policy efficiently to facilitate learning, thus hindering sample efficiency. In this work, we introduce MEReQ (Maximum-Entropy Residual-Q Inverse Reinforcement Learning), designed for sample-efficient alignment from human intervention. Instead of inferring the complete human behavior characteristics, MEReQ infers a residual reward function that captures the discrepancy between the human expert's and the prior policy's underlying reward functions. It then employs Residual Q-Learning (RQL) to align the policy with human preferences using this residual reward function. Extensive evaluations on simulated and real-world tasks demonstrate that MEReQ achieves sample-efficient policy alignment from human intervention.
The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models (LLMs) and multimodal LLMs (MLLMs) for embodied tasks suffer from key limitations, including a significant gap between model design and agent requirements, an unavoidable trade-off between real-time latency and performance, and the use of unauthentic, offline evaluation metrics. To address these challenges, we propose EmbodiedBrain, a novel vision-language foundation model available in both 7B and 32B parameter sizes. Our framework features an agent-aligned data structure and employs a powerful training methodology that integrates large-scale Supervised Fine-Tuning (SFT) with Step-Augumented Group Relative Policy Optimization (Step-GRPO), which boosts long-horizon task success by integrating preceding steps as Guided Precursors. Furthermore, we incorporate a comprehensive reward system, including a Generative Reward Model (GRM) accelerated at the infrastructure level, to improve training efficiency. For enable thorough validation, we establish a three-part evaluation system encompassing General, Planning, and End-to-End Simulation Benchmarks, highlighted by the proposal and open-sourcing of a novel, challenging simulation environment. Experimental results demonstrate that EmbodiedBrain achieves superior performance across all metrics, establishing a new state-of-the-art for embodied foundation models. Towards paving the way for the next generation of generalist embodied agents, we open-source all of our data, model weight, and evaluating methods, which are available at https://zterobot.github.io/EmbodiedBrain.github.io.
Realistic 3D indoor scene synthesis is vital for embodied AI and digital content creation. It can be naturally divided into two subtasks: object generation and layout generation. While recent generative models have significantly advanced object-level quality and controllability, layout generation remains challenging due to limited datasets. Existing methods either overfit to these datasets or rely on predefined constraints to optimize numerical layout that sacrifice flexibility. As a result, they fail to generate scenes that are both open-vocabulary and aligned with fine-grained user instructions. We introduce DirectLayout, a framework that directly generates numerical 3D layouts from text descriptions using generalizable spatial reasoning of large language models (LLMs). DirectLayout decomposes the generation into three stages: producing a Bird's-Eye View (BEV) layout, lifting it into 3D space, and refining object placements. To enable explicit spatial reasoning and help the model grasp basic principles of object placement, we employ Chain-of-Thought (CoT) Activation based on the 3D-Front dataset. Additionally, we design CoT-Grounded Generative Layout Reward to enhance generalization and spatial planning. During inference, DirectLayout addresses asset-layout mismatches via Iterative Asset-Layout Alignment through in-context learning. Extensive experiments demonstrate that DirectLayout achieves impressive semantic consistency, generalization and physical plausibility.
The realization of Artificial General Intelligence (AGI) necessitates Embodied AI agents capable of robust spatial perception, effective task planning, and adaptive execution in physical environments. However, current large language models (LLMs) and multimodal LLMs (MLLMs) for embodied tasks suffer from key limitations, including a significant gap between model design and agent requirements, an unavoidable trade-off between real-time latency and performance, and the use of unauthentic, offline evaluation metrics. To address these challenges, we propose EmbodiedBrain, a novel vision-language foundation model available in both 7B and 32B parameter sizes. Our framework features an agent-aligned data structure and employs a powerful training methodology that integrates large-scale Supervised Fine-Tuning (SFT) with Step-Augumented Group Relative Policy Optimization (Step-GRPO), which boosts long-horizon task success by integrating preceding steps as Guided Precursors. Furthermore, we incorporate a comprehensive reward system, including a Generative Reward Model (GRM) accelerated at the infrastructure level, to improve training efficiency. For enable thorough validation, we establish a three-part evaluation system encompassing General, Planning, and End-to-End Simulation Benchmarks, highlighted by the proposal and open-sourcing of a novel, challenging simulation environment. Experimental results demonstrate that EmbodiedBrain achieves superior performance across all metrics, establishing a new state-of-the-art for embodied foundation models. Towards paving the way for the next generation of generalist embodied agents, we open-source all of our data, model weight, and evaluating methods, which are available at https://zterobot.github.io/EmbodiedBrain.github.io.
Realistic 3D indoor scene synthesis is vital for embodied AI and digital content creation. It can be naturally divided into two subtasks: object generation and layout generation. While recent generative models have significantly advanced object-level quality and controllability, layout generation remains challenging due to limited datasets. Existing methods either overfit to these datasets or rely on predefined constraints to optimize numerical layout that sacrifice flexibility. As a result, they fail to generate scenes that are both open-vocabulary and aligned with fine-grained user instructions. We introduce DirectLayout, a framework that directly generates numerical 3D layouts from text descriptions using generalizable spatial reasoning of large language models (LLMs). DirectLayout decomposes the generation into three stages: producing a Bird's-Eye View (BEV) layout, lifting it into 3D space, and refining object placements. To enable explicit spatial reasoning and help the model grasp basic principles of object placement, we employ Chain-of-Thought (CoT) Activation based on the 3D-Front dataset. Additionally, we design CoT-Grounded Generative Layout Reward to enhance generalization and spatial planning. During inference, DirectLayout addresses asset-layout mismatches via Iterative Asset-Layout Alignment through in-context learning. Extensive experiments demonstrate that DirectLayout achieves impressive semantic consistency, generalization and physical plausibility.
Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.
Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D
Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face distinct limitations: video-based methods generate diverse content but lack real-time physics feedback for interactive learning, while physics-based engines provide accurate dynamics but face scalability limitations from costly manual asset creation. We present Seed3D 1.0, a foundation model that generates simulation-ready 3D assets from single images, addressing the scalability challenge while maintaining physics rigor. Unlike existing 3D generation models, our system produces assets with accurate geometry, well-aligned textures, and realistic physically-based materials. These assets can be directly integrated into physics engines with minimal configuration, enabling deployment in robotic manipulation and simulation training. Beyond individual objects, the system scales to complete scene generation through assembling objects into coherent environments. By enabling scalable simulation-ready content creation, Seed3D 1.0 provides a foundation for advancing physics-based world simulators. Seed3D 1.0 is now available on https://console.volcengine.com/ark/region:ark+cn-beijing/experience/vision?modelId=doubao-seed3d-1-0-250928&tab=Gen3D
In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce $\textbf{AutoPage}$, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfectly with the author's vision, transforming the system from a mere tool into a powerful collaborative assistant. To rigorously validate our approach, we also construct $\textbf{PageBench}$, the first benchmark for this new task. Experiments show AutoPage not only generates high-quality, visually appealing pages but does so with remarkable efficiency in under 15 minutes for less than \$0.1. Code and dataset will be released at $\href{https://mqleet.github.io/AutoPage_ProjectPage/}{Webpage}$.
Vision-language models (VLMs) are essential to Embodied AI, enabling robots to perceive, reason, and act in complex environments. They also serve as the foundation for the recent Vision-Language-Action (VLA) models. Yet most evaluations of VLMs focus on single-view settings, leaving their ability to integrate multi-view information underexplored. At the same time, multi-camera setups are increasingly standard in robotic platforms, as they provide complementary perspectives to mitigate occlusion and depth ambiguity. Whether VLMs can effectively leverage such multi-view inputs for robotic reasoning therefore remains an open question. To bridge this gap, we introduce MV-RoboBench, a benchmark specifically designed to evaluate the multi-view spatial reasoning capabilities of VLMs in robotic manipulation. MV-RoboBench consists of 1.7k manually curated QA items across eight subtasks, divided into two primary categories: spatial understanding and robotic execution. We evaluate a diverse set of existing VLMs, including both open-source and closed-source models, along with enhanced versions incorporating CoT-inspired techniques. The results show that state-of-the-art models remain far below human performance, underscoring the substantial challenges VLMs face in multi-view robotic perception. Additionally, our analysis uncovers two key findings: (i) spatial intelligence and robotic task execution are positively correlated in multi-view robotic scenarios; and (ii) strong performance on existing general-purpose single-view spatial understanding benchmarks does not reliably translate to success in the robotic spatial tasks assessed by our benchmark. We release MV-RoboBench as an open resource to foster progress in spatially grounded VLMs and VLAs, providing not only data but also a standardized evaluation protocol for multi-view embodied reasoning.
Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often overfit and fail to generalize OOD. Existing neural network-based agents typically increase architectural complexity that paradoxically become counterproductive in the small-sample regime. This paper introduce NeuRO, a integrated learning-to-optimize framework that tightly couples perception networks with downstream task-level robust optimization. Specifically, NeuRO addresses core difficulties in this integration: (i) it transforms noisy visual predictions under data scarcity into convex uncertainty sets using Partially Input Convex Neural Networks (PICNNs) with conformal calibration, which directly parameterize the optimization constraints; and (ii) it reformulates planning under partial observability as a robust optimization problem, enabling uncertainty-aware policies that transfer across environments. Extensive experiments on both unordered and sequential multi-object navigation tasks demonstrate that NeuRO establishes SoTA performance, particularly in generalization to unseen environments. Our work thus presents a significant advancement for developing robust, generalizable autonomous agents.
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support perception, prediction, and decision making. This survey presents a unified framework for world models in embodied AI. Specifically, we formalize the problem setting and learning objectives, and propose a three-axis taxonomy encompassing: (1) Functionality, Decision-Coupled vs. General-Purpose; (2) Temporal Modeling, Sequential Simulation and Inference vs. Global Difference Prediction; (3) Spatial Representation, Global Latent Vector, Token Feature Sequence, Spatial Latent Grid, and Decomposed Rendering Representation. We systematize data resources and metrics across robotics, autonomous driving, and general video settings, covering pixel prediction quality, state-level understanding, and task performance. Furthermore, we offer a quantitative comparison of state-of-the-art models and distill key open challenges, including the scarcity of unified datasets and the need for evaluation metrics that assess physical consistency over pixel fidelity, the trade-off between model performance and the computational efficiency required for real-time control, and the core modeling difficulty of achieving long-horizon temporal consistency while mitigating error accumulation. Finally, we maintain a curated bibliography at https://github.com/Li-Zn-H/AwesomeWorldModels.
The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a unified bridging framework. This work provides a comprehensive overview of physical AI, establishing clear distinctions between theoretical physics reasoning and applied physical understanding while systematically examining how physics-grounded methods enhance AI's real-world comprehension across structured symbolic reasoning, embodied systems, and generative models. Through rigorous analysis of recent advances, we advocate for intelligent systems that ground learning in both physical principles and embodied reasoning processes, transcending pattern recognition toward genuine understanding of physical laws. Our synthesis envisions next-generation world models capable of explaining physical phenomena and predicting future states, advancing safe, generalizable, and interpretable AI systems. We maintain a continuously updated resource at https://github.com/AI4Phys/Awesome-AI-for-Physics.
Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often overfit and fail to generalize OOD. Existing neural network-based agents typically increase architectural complexity that paradoxically become counterproductive in the small-sample regime. This paper introduce NeuRO, a integrated learning-to-optimize framework that tightly couples perception networks with downstream task-level robust optimization. Specifically, NeuRO addresses core difficulties in this integration: (i) it transforms noisy visual predictions under data scarcity into convex uncertainty sets using Partially Input Convex Neural Networks (PICNNs) with conformal calibration, which directly parameterize the optimization constraints; and (ii) it reformulates planning under partial observability as a robust optimization problem, enabling uncertainty-aware policies that transfer across environments. Extensive experiments on both unordered and sequential multi-object navigation tasks demonstrate that NeuRO establishes SoTA performance, particularly in generalization to unseen environments. Our work thus presents a significant advancement for developing robust, generalizable autonomous agents.
Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have leveraged large language models (LLMs) for multi-agent planning, a few have begun to explore vision-language models (VLMs) for visual reasoning. However, these VLM-based approaches remain limited in their support for diverse embodiment types. In this work, we introduce VIKI-Bench, the first hierarchical benchmark tailored for embodied multi-agent cooperation, featuring three structured levels: agent activation, task planning, and trajectory perception. VIKI-Bench includes diverse robot embodiments, multi-view visual observations, and structured supervision signals to evaluate reasoning grounded in visual inputs. To demonstrate the utility of VIKI-Bench, we propose VIKI-R, a two-stage framework that fine-tunes a pretrained vision-language model (VLM) using Chain-of-Thought annotated demonstrations, followed by reinforcement learning under multi-level reward signals. Our extensive experiments show that VIKI-R significantly outperforms baselines method across all task levels. Furthermore, we show that reinforcement learning enables the emergence of compositional cooperation patterns among heterogeneous agents. Together, VIKI-Bench and VIKI-R offer a unified testbed and method for advancing multi-agent, visual-driven cooperation in embodied AI systems.
Large Language Models (LLMs), as the foundational architecture for next-generation interactive AI applications, not only power intelligent dialogue systems but also drive the evolution of embodied intelligence on edge devices, including humanoid robots, smart vehicles, and other scenarios. The applications running on these edge devices impose differentiated Service Level Objectives (SLO) requirements on LLM services, specifically manifested as distinct constraints on Time to First Token (TTFT) and Time Per Output Token (TPOT) as well as end-to-end latency. Notably, edge devices typically handle real-time tasks that are extremely sensitive to latency, such as machine control and navigation planning. However, existing scheduling service systems still prioritize maximizing output token throughput as the sole optimization objective, failing to adequately address the diversity of SLO requirements. This ultimately results in persistently high violation rates for end-to-end latency or TPOT related SLOs. This paper proposes SLICE, an innovative scheduling solution designed for edge computing scenarios with differentiated SLO requirements. By combining a utility-maximizing request scheduling algorithm with a dynamic iterative control mechanism for generation rates, SLICE significantly improves LLM inference service SLO attainment. Experimental results demonstrate that compared to state-of-the-art solutions Orca and FastServe, SLICE achieves up to 35x higher SLO attainment and 3.4x advantage in task completion time than the other two solutions.
As large language models (LLMs) evolve, their integration with 3D spatial data (3D-LLMs) has seen rapid progress, offering unprecedented capabilities for understanding and interacting with physical spaces. This survey provides a comprehensive overview of the methodologies enabling LLMs to process, understand, and generate 3D data. Highlighting the unique advantages of LLMs, such as in-context learning, step-by-step reasoning, open-vocabulary capabilities, and extensive world knowledge, we underscore their potential to significantly advance spatial comprehension and interaction within embodied Artificial Intelligence (AI) systems. Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs). It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue, as well as LLM-based agents for spatial reasoning, planning, and navigation. The paper also includes a brief review of other methods that integrate 3D and language. The meta-analysis presented in this paper reveals significant progress yet underscores the necessity for novel approaches to harness the full potential of 3D-LLMs. Hence, with this paper, we aim to chart a course for future research that explores and expands the capabilities of 3D-LLMs in understanding and interacting with the complex 3D world. To support this survey, we have established a project page where papers related to our topic are organized and listed: https://github.com/ActiveVisionLab/Awesome-LLM-3D.
Robotic systems are increasingly expected to operate in human-centered, unstructured environments where safety, adaptability, and generalization are essential. Vision-Language-Action (VLA) models have been proposed as a language guided generalized control framework for real robots. However, their deployment has been limited to conventional serial link manipulators. Coupled by their rigidity and unpredictability of learning based control, the ability to safely interact with the environment is missing yet critical. In this work, we present the deployment of a VLA model on a soft continuum manipulator to demonstrate autonomous safe human-robot interaction. We present a structured finetuning and deployment pipeline evaluating two state-of-the-art VLA models (OpenVLA-OFT and $\pi_0$) across representative manipulation tasks, and show while out-of-the-box policies fail due to embodiment mismatch, through targeted finetuning the soft robot performs equally to the rigid counterpart. Our findings highlight the necessity of finetuning for bridging embodiment gaps, and demonstrate that coupling VLA models with soft robots enables safe and flexible embodied AI in human-shared environments.
Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have attracted widespread attention for their remarkable capabilities in multimodal data understanding. Meanwhile, the rapid expansion of information services has led to a growing demand for AI-enabled wireless networks. The open-source DeepSeek models are famous for their innovative designs, such as large-scale pure RL and cost-efficient training, which make them well-suited for practical deployment in wireless networks. By integrating DeepSeek-style LLMs with wireless infrastructures, a synergistic opportunity arises: the DeepSeek-style LLMs enhance network optimization with strong reasoning and decision-making abilities, while wireless infrastructure enables the broad deployment of these models. Motivated by this convergence, this survey presents a comprehensive DeepSeek-inspired exploration of RL-based LLMs in the context of wireless networks. We begin by reviewing key techniques behind network optimization to establish a foundation for understanding DeepSeek-style LLM integration. Next, we examine recent advancements in RL-based LLMs, using DeepSeek models as a representative example. Building on this, we explore the synergy between the two domains, highlighting motivations, challenges, and potential solutions. Finally, we highlight emerging directions for integrating LLMs with wireless networks, such as quantum, on-device, and neural-symbolic LLM models, as well as embodied AI agents. Overall, this survey offers a comprehensive examination of the interplay between DeepSeek-style LLMs and wireless networks, demonstrating how these domains can mutually enhance each other to drive innovation.
Recognizing the sounding objects in scenes is a longstanding objective in embodied AI, with diverse applications in robotics and AR/VR/MR. To that end, Audio-Visual Segmentation (AVS), taking as condition an audio signal to identify the masks of the target sounding objects in an input image with synchronous camera and microphone sensors, has been recently advanced. However, this paradigm is still insufficient for real-world operation, as the mapping from 2D images to 3D scenes is missing. To address this fundamental limitation, we introduce a novel research problem, 3D Audio-Visual Segmentation, extending the existing AVS to the 3D output space. This problem poses more challenges due to variations in camera extrinsics, audio scattering, occlusions, and diverse acoustics across sounding object categories. To facilitate this research, we create the very first simulation based benchmark, 3DAVS-S34-O7, providing photorealistic 3D scene environments with grounded spatial audio under single-instance and multi-instance settings, across 34 scenes and 7 object categories. This is made possible by re-purposing the Habitat simulator to generate comprehensive annotations of sounding object locations and corresponding 3D masks. Subsequently, we propose a new approach, EchoSegnet, characterized by integrating the ready-to-use knowledge from pretrained 2D audio-visual foundation models synergistically with 3D visual scene representation through spatial audio-aware mask alignment and refinement. Extensive experiments demonstrate that EchoSegnet can effectively segment sounding objects in 3D space on our new benchmark, representing a significant advancement in the field of embodied AI. Project page: https://x-up-lab.github.io/research/3d-audio-visual-segmentation/
Recognizing the sounding objects in scenes is a longstanding objective in embodied AI, with diverse applications in robotics and AR/VR/MR. To that end, Audio-Visual Segmentation (AVS), taking as condition an audio signal to identify the masks of the target sounding objects in an input image with synchronous camera and microphone sensors, has been recently advanced. However, this paradigm is still insufficient for real-world operation, as the mapping from 2D images to 3D scenes is missing. To address this fundamental limitation, we introduce a novel research problem, 3D Audio-Visual Segmentation, extending the existing AVS to the 3D output space. This problem poses more challenges due to variations in camera extrinsics, audio scattering, occlusions, and diverse acoustics across sounding object categories. To facilitate this research, we create the very first simulation based benchmark, 3DAVS-S34-O7, providing photorealistic 3D scene environments with grounded spatial audio under single-instance and multi-instance settings, across 34 scenes and 7 object categories. This is made possible by re-purposing the Habitat simulator to generate comprehensive annotations of sounding object locations and corresponding 3D masks. Subsequently, we propose a new approach, EchoSegnet, characterized by integrating the ready-to-use knowledge from pretrained 2D audio-visual foundation models synergistically with 3D visual scene representation through spatial audio-aware mask alignment and refinement. Extensive experiments demonstrate that EchoSegnet can effectively segment sounding objects in 3D space on our new benchmark, representing a significant advancement in the field of embodied AI. Project page: https://x-up-lab.github.io/research/3d-audio-visual-segmentation/
Robotic systems are increasingly expected to operate in human-centered, unstructured environments where safety, adaptability, and generalization are essential. Vision-Language-Action (VLA) models have been proposed as a language guided generalized control framework for real robots. However, their deployment has been limited to conventional serial link manipulators. Coupled by their rigidity and unpredictability of learning based control, the ability to safely interact with the environment is missing yet critical. In this work, we present the deployment of a VLA model on a soft continuum manipulator to demonstrate autonomous safe human-robot interaction. We present a structured finetuning and deployment pipeline evaluating two state-of-the-art VLA models (OpenVLA-OFT and $Ï€_0$) across representative manipulation tasks, and show while out-of-the-box policies fail due to embodiment mismatch, through targeted finetuning the soft robot performs equally to the rigid counterpart. Our findings highlight the necessity of finetuning for bridging embodiment gaps, and demonstrate that coupling VLA models with soft robots enables safe and flexible embodied AI in human-shared environments.
Reinforcement learning (RL)-based large language models (LLMs), such as ChatGPT, DeepSeek, and Grok-3, have attracted widespread attention for their remarkable capabilities in multimodal data understanding. Meanwhile, the rapid expansion of information services has led to a growing demand for AI-enabled wireless networks. The open-source DeepSeek models are famous for their innovative designs, such as large-scale pure RL and cost-efficient training, which make them well-suited for practical deployment in wireless networks. By integrating DeepSeek-style LLMs with wireless infrastructures, a synergistic opportunity arises: the DeepSeek-style LLMs enhance network optimization with strong reasoning and decision-making abilities, while wireless infrastructure enables the broad deployment of these models. Motivated by this convergence, this survey presents a comprehensive DeepSeek-inspired exploration of RL-based LLMs in the context of wireless networks. We begin by reviewing key techniques behind network optimization to establish a foundation for understanding DeepSeek-style LLM integration. Next, we examine recent advancements in RL-based LLMs, using DeepSeek models as a representative example. Building on this, we explore the synergy between the two domains, highlighting motivations, challenges, and potential solutions. Finally, we highlight emerging directions for integrating LLMs with wireless networks, such as quantum, on-device, and neural-symbolic LLM models, as well as embodied AI agents. Overall, this survey offers a comprehensive examination of the interplay between DeepSeek-style LLMs and wireless networks, demonstrating how these domains can mutually enhance each other to drive innovation.
In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to quickly adapt to new tasks? A prerequisite for embodied agents deployed in real world interactions ought to be training with interaction, yet today's most successful AI models (e.g., VLMs, LLMs) are trained without an explicit notion of action. The problem of pure exploration (which assumes no data as input) is well studied in the reinforcement learning literature and provides agents with a wide array of experiences, yet it fails to prepare them for rapid adaptation to new tasks. Today's language and vision models are trained on data provided by humans, which provides a strong inductive bias for the sorts of tasks that the model will have to solve (e.g., modeling chords in a song, phrases in a sonnet, sentences in a medical record). However, when they are prompted to solve a new task, there is a faulty tacit assumption that humans spend most of their time in the most rewarding states. The key contribution of our paper is a method for pre-training interactive agents in a self-supervised fashion, so that they can instantly mimic human demonstrations. Our method treats goals (i.e., observations) as the atomic construct. During training, our method automatically proposes goals and practices reaching them, building off prior work in reinforcement learning exploration. During evaluation, our method solves an (amortized) inverse reinforcement learning problem to explain demonstrations as optimal goal-reaching behavior. Experiments on standard benchmarks (not designed for goal-reaching) show that our approach outperforms prior methods for zero-shot imitation.
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support perception, prediction, and decision making. This survey presents a unified framework for world models in embodied AI. Specifically, we formalize the problem setting and learning objectives, and propose a three-axis taxonomy encompassing: (1) Functionality, Decision-Coupled vs. General-Purpose; (2) Temporal Modeling, Sequential Simulation and Inference vs. Global Difference Prediction; (3) Spatial Representation, Global Latent Vector, Token Feature Sequence, Spatial Latent Grid, and Decomposed Rendering Representation. We systematize data resources and metrics across robotics, autonomous driving, and general video settings, covering pixel prediction quality, state-level understanding, and task performance. Furthermore, we offer a quantitative comparison of state-of-the-art models and distill key open challenges, including the scarcity of unified datasets and the need for evaluation metrics that assess physical consistency over pixel fidelity, the trade-off between model performance and the computational efficiency required for real-time control, and the core modeling difficulty of achieving long-horizon temporal consistency while mitigating error accumulation. Finally, we maintain a curated bibliography at https://github.com/Li-Zn-H/AwesomeWorldModels.
Embodied AI requires agents that perceive, act, and anticipate how actions reshape future world states. World models serve as internal simulators that capture environment dynamics, enabling forward and counterfactual rollouts to support perception, prediction, and decision making. This survey presents a unified framework for world models in embodied AI. Specifically, we formalize the problem setting and learning objectives, and propose a three-axis taxonomy encompassing: (1) Functionality, Decision-Coupled vs. General-Purpose; (2) Temporal Modeling, Sequential Simulation and Inference vs. Global Difference Prediction; (3) Spatial Representation, Global Latent Vector, Token Feature Sequence, Spatial Latent Grid, and Decomposed Rendering Representation. We systematize data resources and metrics across robotics, autonomous driving, and general video settings, covering pixel prediction quality, state-level understanding, and task performance. Furthermore, we offer a quantitative comparison of state-of-the-art models and distill key open challenges, including the scarcity of unified datasets and the need for evaluation metrics that assess physical consistency over pixel fidelity, the trade-off between model performance and the computational efficiency required for real-time control, and the core modeling difficulty of achieving long-horizon temporal consistency while mitigating error accumulation. Finally, we maintain a curated bibliography at https://github.com/Li-Zn-H/AwesomeWorldModels.
The rapid advancement of embodied intelligence and world models has intensified efforts to integrate physical laws into AI systems, yet physical perception and symbolic physics reasoning have developed along separate trajectories without a unified bridging framework. This work provides a comprehensive overview of physical AI, establishing clear distinctions between theoretical physics reasoning and applied physical understanding while systematically examining how physics-grounded methods enhance AI's real-world comprehension across structured symbolic reasoning, embodied systems, and generative models. Through rigorous analysis of recent advances, we advocate for intelligent systems that ground learning in both physical principles and embodied reasoning processes, transcending pattern recognition toward genuine understanding of physical laws. Our synthesis envisions next-generation world models capable of explaining physical phenomena and predicting future states, advancing safe, generalizable, and interpretable AI systems. We maintain a continuously updated resource at https://github.com/AI4Phys/Awesome-AI-for-Physics.
In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and undermine the rich visual perception signals present in the data, which are critical for tasks involving spatial reasoning in the domain of embodied AI and robotics. Is it possible to optimize both at the same time? In this work, we propose VisPer-LM, the first approach that infuses visual perception knowledge from expert vision encoders into the LLM's (of an MLLM) hidden representations. We start by investigating MLLMs trained solely with natural language supervision and identify a positive correlation between the quality of visual representations within these models and their downstream performance. Given this insight, we formulate the objective during the pretraining stage in MLLMs as a coupled optimization of predictive visual embedding and next (text) token prediction. Moreover, through extensive probing, we observe improved visual representation quality due to embedding optimization, underscoring the effectiveness of our probing setup. We demonstrate that our VisPer-LM outperforms the single and multi-encoder baselines, proving our approach's superiority over explicitly feeding the corresponding features to the LLM. In particular, VisPer-LM boosts performance by an average margin of up to 2.5% on various benchmarks, with a notable improvement of 8.7% on the Depth task in CV-Bench.
In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and undermine the rich visual perception signals present in the data, which are critical for tasks involving spatial reasoning in the domain of embodied AI and robotics. Is it possible to optimize both at the same time? In this work, we propose VisPer-LM, the first approach that infuses visual perception knowledge from expert vision encoders into the LLM's (of an MLLM) hidden representations. We start by investigating MLLMs trained solely with natural language supervision and identify a positive correlation between the quality of visual representations within these models and their downstream performance. Given this insight, we formulate the objective during the pretraining stage in MLLMs as a coupled optimization of predictive visual embedding and next (text) token prediction. Moreover, through extensive probing, we observe improved visual representation quality due to embedding optimization, underscoring the effectiveness of our probing setup. We demonstrate that our VisPer-LM outperforms the single and multi-encoder baselines, proving our approach's superiority over explicitly feeding the corresponding features to the LLM. In particular, VisPer-LM boosts performance by an average margin of up to 2.5% on various benchmarks, with a notable improvement of 8.7% on the Depth task in CV-Bench.
Urban embodied AI agents, ranging from delivery robots to quadrupeds, are increasingly populating our cities, navigating chaotic streets to provide last-mile connectivity. Training such agents requires diverse, high-fidelity urban environments to scale, yet existing human-crafted or procedurally generated simulation scenes either lack scalability or fail to capture real-world complexity. We introduce UrbanVerse, a data-driven real-to-sim system that converts crowd-sourced city-tour videos into physics-aware, interactive simulation scenes. UrbanVerse consists of: (i) UrbanVerse-100K, a repository of 100k+ annotated urban 3D assets with semantic and physical attributes, and (ii) UrbanVerse-Gen, an automatic pipeline that extracts scene layouts from video and instantiates metric-scale 3D simulations using retrieved assets. Running in IsaacSim, UrbanVerse offers 160 high-quality constructed scenes from 24 countries, along with a curated benchmark of 10 artist-designed test scenes. Experiments show that UrbanVerse scenes preserve real-world semantics and layouts, achieving human-evaluated realism comparable to manually crafted scenes. In urban navigation, policies trained in UrbanVerse exhibit scaling power laws and strong generalization, improving success by +6.3% in simulation and +30.1% in zero-shot sim-to-real transfer comparing to prior methods, accomplishing a 300 m real-world mission with only two interventions.
Urban embodied AI agents, ranging from delivery robots to quadrupeds, are increasingly populating our cities, navigating chaotic streets to provide last-mile connectivity. Training such agents requires diverse, high-fidelity urban environments to scale, yet existing human-crafted or procedurally generated simulation scenes either lack scalability or fail to capture real-world complexity. We introduce UrbanVerse, a data-driven real-to-sim system that converts crowd-sourced city-tour videos into physics-aware, interactive simulation scenes. UrbanVerse consists of: (i) UrbanVerse-100K, a repository of 100k+ annotated urban 3D assets with semantic and physical attributes, and (ii) UrbanVerse-Gen, an automatic pipeline that extracts scene layouts from video and instantiates metric-scale 3D simulations using retrieved assets. Running in IsaacSim, UrbanVerse offers 160 high-quality constructed scenes from 24 countries, along with a curated benchmark of 10 artist-designed test scenes. Experiments show that UrbanVerse scenes preserve real-world semantics and layouts, achieving human-evaluated realism comparable to manually crafted scenes. In urban navigation, policies trained in UrbanVerse exhibit scaling power laws and strong generalization, improving success by +6.3% in simulation and +30.1% in zero-shot sim-to-real transfer comparing to prior methods, accomplishing a 300 m real-world mission with only two interventions.
Understanding fine-grained actions and accurately localizing their corresponding actors in space and time are fundamental capabilities for advancing next-generation AI systems, including embodied agents, autonomous platforms, and human-AI interaction frameworks. Despite recent progress in video understanding, existing methods predominantly address either coarse-grained action recognition or generic object tracking, thereby overlooking the challenge of jointly detecting and tracking multiple objects according to their actions while grounding them temporally. To address this gap, we introduce Spatio-temporal Video Action Grounding (SVAG), a novel task that requires models to simultaneously detect, track, and temporally localize all referent objects in videos based on natural language descriptions of their actions. To support this task, we construct SVAG-Bench, a large-scale benchmark comprising 688 videos, 19,590 annotated records, and 903 unique verbs, covering a diverse range of objects, actions, and real-world scenes. We further propose SVAGFormer, a baseline framework that adapts state of the art vision language models for joint spatial and temporal grounding, and introduce SVAGEval, a standardized evaluation toolkit for fair and reproducible benchmarking. Empirical results show that existing models perform poorly on SVAG, particularly in dense or complex scenes, underscoring the need for more advanced reasoning over fine-grained object-action interactions in long videos.
Recent success with large language models has sparked a new wave of verbal human-AI interaction. While such models support users in a variety of creative tasks, they lack the embodied nature of human interaction. Dance, as a primal form of human expression, is predestined to complement this experience. To explore creative human-AI interaction exemplified by dance, we build an interactive model based on motion capture (MoCap) data. It generates an artificial other by partially mimicking and also "creatively" enhancing an incoming sequence of movement data. It is the first model, which leverages single-person motion data and high level features in order to do so and, thus, it does not rely on low level human-human interaction data. It combines ideas of two diffusion models, motion inpainting, and motion style transfer to generate movement representations that are both temporally coherent and responsive to a chosen movement reference. The success of the model is demonstrated by quantitatively assessing the convergence of the feature distribution of the generated samples and the test set which serves as simulating the human performer. We show that our generations are first steps to creative dancing with AI as they are both diverse showing various deviations from the human partner while appearing realistic.
Envision an AI capable of functioning in human-like settings, moving beyond mere observation to actively understand, anticipate, and proactively respond to unfolding events. Towards this vision, we focus on the innovative task where, given ego-streaming video input, an assistant proactively answers diverse, evolving questions at the opportune moment, while maintaining synchronized perception and reasoning. This task embodies three key properties: (1) Proactive Coherence, (2) Just-in-Time Responsiveness, and (3) Synchronized Efficiency. To evaluate and address these properties, we first introduce ESTP-Bench (Ego Streaming Proactive Benchmark) alongside the ESTP-F1 metric-a novel framework designed for their rigorous assessment. Secondly, we propose a comprehensive technical pipeline to enable models to tackle this challenging task. This pipeline comprises: (1) a data engine, (2) a multi-stage training strategy, and (3) a proactive dynamic compression technique. Our proposed model effectively addresses these critical properties while outperforming multiple baselines across diverse online and offline benchmarks. Project Page:https://zhangyl4.github.io/publications/eyes-wide-open/
With the rapid proliferation of large language models and vision-language models, AI agents have evolved from isolated, task-specific systems into autonomous, interactive entities capable of perceiving, reasoning, and acting without human intervention. As these agents proliferate across virtual and physical environments, from virtual assistants to embodied robots, the need for a unified, agent-centric infrastructure becomes paramount. In this survey, we introduce the Internet of Agents (IoA) as a foundational framework that enables seamless interconnection, dynamic discovery, and collaborative orchestration among heterogeneous agents at scale. We begin by presenting a general IoA architecture, highlighting its hierarchical organization, distinguishing features relative to the traditional Internet, and emerging applications. Next, we analyze the key operational enablers of IoA, including capability notification and discovery, adaptive communication protocols, dynamic task matching, consensus and conflict-resolution mechanisms, and incentive models. Finally, we identify open research directions toward building resilient and trustworthy IoA ecosystems.
We present Human Motions with Objects (HUMOTO), a high-fidelity dataset of human-object interactions for motion generation, computer vision, and robotics applications. Featuring 735 sequences (7,875 seconds at 30 fps), HUMOTO captures interactions with 63 precisely modeled objects and 72 articulated parts. Our innovations include a scene-driven LLM scripting pipeline creating complete, purposeful tasks with natural progression, and a mocap-and-camera recording setup to effectively handle occlusions. Spanning diverse activities from cooking to outdoor picnics, HUMOTO preserves both physical accuracy and logical task flow. Professional artists rigorously clean and verify each sequence, minimizing foot sliding and object penetrations. We also provide benchmarks compared to other datasets. HUMOTO's comprehensive full-body motion and simultaneous multi-object interactions address key data-capturing challenges and provide opportunities to advance realistic human-object interaction modeling across research domains with practical applications in animation, robotics, and embodied AI systems. Project: https://jiaxin-lu.github.io/humoto/ .
In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks.
Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often overfit and fail to generalize OOD. Existing neural network-based agents typically increase architectural complexity that paradoxically become counterproductive in the small-sample regime. This paper introduce NeuRO, a integrated learning-to-optimize framework that tightly couples perception networks with downstream task-level robust optimization. Specifically, NeuRO addresses core difficulties in this integration: (i) it transforms noisy visual predictions under data scarcity into convex uncertainty sets using Partially Input Convex Neural Networks (PICNNs) with conformal calibration, which directly parameterize the optimization constraints; and (ii) it reformulates planning under partial observability as a robust optimization problem, enabling uncertainty-aware policies that transfer across environments. Extensive experiments on both unordered and sequential multi-object navigation tasks demonstrate that NeuRO establishes SoTA performance, particularly in generalization to unseen environments. Our work thus presents a significant advancement for developing robust, generalizable autonomous agents.
Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories, with various distortions in the Real-world limiting its application. Traditionally, Image Quality Assessment (IQA) methods are applied to predict human preferences for distorted images; however, there is no IQA method to assess the usability of an image in embodied tasks, namely, the perceptual quality for robots. To provide accurate and reliable quality indicators for future embodied scenarios, we first propose the topic: IQA for Embodied AI. Specifically, we (1) based on the Mertonian system and meta-cognitive theory, constructed a perception-cognition-decision-execution pipeline and defined a comprehensive subjective score collection process; (2) established the Embodied-IQA database, containing over 36k reference/distorted image pairs, with more than 5m fine-grained annotations provided by Vision Language Models/Vision Language Action-models/Real-world robots; (3) trained and validated the performance of mainstream IQA methods on Embodied-IQA, demonstrating the need to develop more accurate quality indicators for Embodied AI. We sincerely hope that through evaluation, we can promote the application of Embodied AI under complex distortions in the Real-world. Project page: https://github.com/lcysyzxdxc/EmbodiedIQA
In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient methods to incorporate changes are needed to maintain up-to-date, high-quality reconstructions without the computational overhead of re-optimizing the entire scene. This paper introduces CL-Splats, which incrementally updates Gaussian splatting-based 3D representations from sparse scene captures. CL-Splats integrates a robust change-detection module that segments updated and static components within the scene, enabling focused, local optimization that avoids unnecessary re-computation. Moreover, CL-Splats supports storing and recovering previous scene states, facilitating temporal segmentation and new scene-analysis applications. Our extensive experiments demonstrate that CL-Splats achieves efficient updates with improved reconstruction quality over the state-of-the-art. This establishes a robust foundation for future real-time adaptation in 3D scene reconstruction tasks.
As the global reach of online higher education continues to grow, universities are increasingly accommodating students from diverse cultural backgrounds (Tereshko et al., 2024). This can present a number of challenges including linguistic barriers (Ullah et al., 2021), cultural differences in learning style (Omidvar & Tan, 2012), cultural sensitivity in course design (Nguyen, 2022) and perceived isolation when students feel their perspectives or experiences are not reflected or valued in the learning environment (Hansen-Brown et al., 2022). Ensuring active engagement and reasonable learning outcomes in such a environments requires distance educational systems that are not only adaptive but also culturally resonant (Dalle et al., 2024). Both embodied and virtual AI-Agents have great potential in this regard as they can facilitate personalized learning and adapt their interactions and content delivery to align with students' cultural context. In addition, Generative AI (GAI), such as, Large Language Models (LLMs) can amplify the potential for these culturally aware AI agents to address educational challenges due to their advanced capacity for understanding and generating contextually relevant content (Wang et al., 2024). This chapter reviews existing research and suggests the usage of culturally aware AI-Agents, powered by GAI, to foster engagement and improve learning outcomes in culturally diverse online higher education environments.
The meteoric rise of AI, with its rapidly expanding market capitalization, presents both transformative opportunities and critical challenges. Chief among these is the urgent need for a new, unified paradigm for trustworthy evaluation, as current benchmarks increasingly reveal critical vulnerabilities. Issues like data contamination and selective reporting by model developers fuel hype, while inadequate data quality control can lead to biased evaluations that, even if unintentionally, may favor specific approaches. As a flood of participants enters the AI space, this "Wild West" of assessment makes distinguishing genuine progress from exaggerated claims exceptionally difficult. Such ambiguity blurs scientific signals and erodes public confidence, much as unchecked claims would destabilize financial markets reliant on credible oversight from agencies like Moody's. In high-stakes human examinations (e.g., SAT, GRE), substantial effort is devoted to ensuring fairness and credibility; why settle for less in evaluating AI, especially given its profound societal impact? This position paper argues that the current laissez-faire approach is unsustainable. We contend that true, sustainable AI advancement demands a paradigm shift: a unified, live, and quality-controlled benchmarking framework robust by construction, not by mere courtesy and goodwill. To this end, we dissect the systemic flaws undermining today's AI evaluation, distill the essential requirements for a new generation of assessments, and introduce PeerBench (with its prototype implementation at https://www.peerbench.ai/), a community-governed, proctored evaluation blueprint that embodies this paradigm through sealed execution, item banking with rolling renewal, and delayed transparency. Our goal is to pave the way for evaluations that can restore integrity and deliver genuinely trustworthy measures of AI progress.
We present Human Motions with Objects (HUMOTO), a high-fidelity dataset of human-object interactions for motion generation, computer vision, and robotics applications. Featuring 735 sequences (7,875 seconds at 30 fps), HUMOTO captures interactions with 63 precisely modeled objects and 72 articulated parts. Our innovations include a scene-driven LLM scripting pipeline creating complete, purposeful tasks with natural progression, and a mocap-and-camera recording setup to effectively handle occlusions. Spanning diverse activities from cooking to outdoor picnics, HUMOTO preserves both physical accuracy and logical task flow. Professional artists rigorously clean and verify each sequence, minimizing foot sliding and object penetrations. We also provide benchmarks compared to other datasets. HUMOTO's comprehensive full-body motion and simultaneous multi-object interactions address key data-capturing challenges and provide opportunities to advance realistic human-object interaction modeling across research domains with practical applications in animation, robotics, and embodied AI systems. Project: https://jiaxin-lu.github.io/humoto/ .
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Firstly, VPS designs an adaptive attention-based geometric fusion mechanism to align cross-frame features via enrolling the pose, depth, and optical flow modality, which automatically adjust feature maps for different decoding stages. And a post-matching strategy is integrated to improve identities tracking. In VO, panoptic segmentation results from VPS are combined with the optical flow map to improve the confidence estimation of dynamic objects, which enhances the accuracy of the camera pose estimation and completeness of the depth map generation via the learning-based paradigm. Furthermore, the point-based rendering of SR is beneficial from VO, transforming sparse point clouds into neural fields to synthesize high-fidelity RGB views and twin panoptic views. Extensive experiments on three public datasets demonstrate that our attention-based feature fusion outperforms most existing state-of-the-art methods on the odometry, tracking, segmentation, and novel view synthesis tasks.
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning (RL). The first stage, \textit{Embodied Prior Learning}, distills foundational knowledge from three types of data: (1) Trajectory-Augmented Priors, which enrich existing trajectory data with structured reasoning generated by stronger models; (2) Environment-Anchored Priors, which provide in-environment knowledge and grounding supervision; and (3) External Knowledge Priors, which transfer general knowledge from out-of-environment datasets. In the second stage, we develop an online RL pipeline that builds on these priors to further enhance agent performance. To overcome the inherent challenges in agent RL, including long horizons, sparse rewards, and training instability, we introduce three key designs: self-summarization for context management, dense reward shaping, and turn-level policy optimization. Extensive experiments on both high-level planning (EB-ALFRED) and low-level control (EB-Manipulation) tasks demonstrate that ERA-3B surpasses both prompting-based large models and previous training-based baselines. Specifically, it achieves overall improvements of 8.4\% on EB-ALFRED and 19.4\% on EB-Manipulation over GPT-4o, and exhibits strong generalization to unseen tasks. Overall, ERA offers a practical path toward scalable embodied intelligence, providing methodological insights for future embodied AI systems.
Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories, with various distortions in the Real-world limiting its application. Traditionally, Image Quality Assessment (IQA) methods are applied to predict human preferences for distorted images; however, there is no IQA method to assess the usability of an image in embodied tasks, namely, the perceptual quality for robots. To provide accurate and reliable quality indicators for future embodied scenarios, we first propose the topic: IQA for Embodied AI. Specifically, we (1) based on the Mertonian system and meta-cognitive theory, constructed a perception-cognition-decision-execution pipeline and defined a comprehensive subjective score collection process; (2) established the Embodied-IQA database, containing over 36k reference/distorted image pairs, with more than 5m fine-grained annotations provided by Vision Language Models/Vision Language Action-models/Real-world robots; (3) trained and validated the performance of mainstream IQA methods on Embodied-IQA, demonstrating the need to develop more accurate quality indicators for Embodied AI. We sincerely hope that through evaluation, we can promote the application of Embodied AI under complex distortions in the Real-world. Project page: https://github.com/lcysyzxdxc/EmbodiedIQA
The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts. However, existing datasets typically suffer from limitations in data scale or diversity, sanitized layouts lacking small items, and severe object collisions. To address these shortcomings, we introduce \textbf{InternScenes}, a novel large-scale simulatable indoor scene dataset comprising approximately 40,000 diverse scenes by integrating three disparate scene sources, real-world scans, procedurally generated scenes, and designer-created scenes, including 1.96M 3D objects and covering 15 common scene types and 288 object classes. We particularly preserve massive small items in the scenes, resulting in realistic and complex layouts with an average of 41.5 objects per region. Our comprehensive data processing pipeline ensures simulatability by creating real-to-sim replicas for real-world scans, enhances interactivity by incorporating interactive objects into these scenes, and resolves object collisions by physical simulations. We demonstrate the value of InternScenes with two benchmark applications: scene layout generation and point-goal navigation. Both show the new challenges posed by the complex and realistic layouts. More importantly, InternScenes paves the way for scaling up the model training for both tasks, making the generation and navigation in such complex scenes possible. We commit to open-sourcing the data, models, and benchmarks to benefit the whole community.
Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories, with various distortions in the Real-world limiting its application. Traditionally, Image Quality Assessment (IQA) methods are applied to predict human preferences for distorted images; however, there is no IQA method to assess the usability of an image in embodied tasks, namely, the perceptual quality for robots. To provide accurate and reliable quality indicators for future embodied scenarios, we first propose the topic: IQA for Embodied AI. Specifically, we (1) based on the Mertonian system and meta-cognitive theory, constructed a perception-cognition-decision-execution pipeline and defined a comprehensive subjective score collection process; (2) established the Embodied-IQA database, containing over 36k reference/distorted image pairs, with more than 5m fine-grained annotations provided by Vision Language Models/Vision Language Action-models/Real-world robots; (3) trained and validated the performance of mainstream IQA methods on Embodied-IQA, demonstrating the need to develop more accurate quality indicators for Embodied AI. We sincerely hope that through evaluation, we can promote the application of Embodied AI under complex distortions in the Real-world. Project page: https://github.com/lcysyzxdxc/EmbodiedIQA
The scene perception, understanding, and simulation are fundamental techniques for embodied-AI agents, while existing solutions are still prone to segmentation deficiency, dynamic objects' interference, sensor data sparsity, and view-limitation problems. This paper proposes a novel framework, named SPORTS, for holistic scene understanding via tightly integrating Video Panoptic Segmentation (VPS), Visual Odometry (VO), and Scene Rendering (SR) tasks into an iterative and unified perspective. Firstly, VPS designs an adaptive attention-based geometric fusion mechanism to align cross-frame features via enrolling the pose, depth, and optical flow modality, which automatically adjust feature maps for different decoding stages. And a post-matching strategy is integrated to improve identities tracking. In VO, panoptic segmentation results from VPS are combined with the optical flow map to improve the confidence estimation of dynamic objects, which enhances the accuracy of the camera pose estimation and completeness of the depth map generation via the learning-based paradigm. Furthermore, the point-based rendering of SR is beneficial from VO, transforming sparse point clouds into neural fields to synthesize high-fidelity RGB views and twin panoptic views. Extensive experiments on three public datasets demonstrate that our attention-based feature fusion outperforms most existing state-of-the-art methods on the odometry, tracking, segmentation, and novel view synthesis tasks.
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning (RL). The first stage, \textit{Embodied Prior Learning}, distills foundational knowledge from three types of data: (1) Trajectory-Augmented Priors, which enrich existing trajectory data with structured reasoning generated by stronger models; (2) Environment-Anchored Priors, which provide in-environment knowledge and grounding supervision; and (3) External Knowledge Priors, which transfer general knowledge from out-of-environment datasets. In the second stage, we develop an online RL pipeline that builds on these priors to further enhance agent performance. To overcome the inherent challenges in agent RL, including long horizons, sparse rewards, and training instability, we introduce three key designs: self-summarization for context management, dense reward shaping, and turn-level policy optimization. Extensive experiments on both high-level planning (EB-ALFRED) and low-level control (EB-Manipulation) tasks demonstrate that ERA-3B surpasses both prompting-based large models and previous training-based baselines. Specifically, it achieves overall improvements of 8.4\% on EB-ALFRED and 19.4\% on EB-Manipulation over GPT-4o, and exhibits strong generalization to unseen tasks. Overall, ERA offers a practical path toward scalable embodied intelligence, providing methodological insights for future embodied AI systems.
The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts. However, existing datasets typically suffer from limitations in data scale or diversity, sanitized layouts lacking small items, and severe object collisions. To address these shortcomings, we introduce \textbf{InternScenes}, a novel large-scale simulatable indoor scene dataset comprising approximately 40,000 diverse scenes by integrating three disparate scene sources, real-world scans, procedurally generated scenes, and designer-created scenes, including 1.96M 3D objects and covering 15 common scene types and 288 object classes. We particularly preserve massive small items in the scenes, resulting in realistic and complex layouts with an average of 41.5 objects per region. Our comprehensive data processing pipeline ensures simulatability by creating real-to-sim replicas for real-world scans, enhances interactivity by incorporating interactive objects into these scenes, and resolves object collisions by physical simulations. We demonstrate the value of InternScenes with two benchmark applications: scene layout generation and point-goal navigation. Both show the new challenges posed by the complex and realistic layouts. More importantly, InternScenes paves the way for scaling up the model training for both tasks, making the generation and navigation in such complex scenes possible. We commit to open-sourcing the data, models, and benchmarks to benefit the whole community.
Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Existing methods either rely on object-specific priors such as CAD models or templates, or suffer from limited generalization across categories due to pose-shape entanglement and multi-stage pipelines. In this work, we propose a unified, category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image, without requiring templates, CAD models, or category labels at test time. Our model fuses dense 2D features from vision foundation models with partial 3D point clouds using a Transformer encoder enhanced by a Mixture-of-Experts, and employs parallel decoders for pose-size estimation and shape reconstruction, achieving real-time inference at 28 FPS. Trained solely on synthetic data from 149 categories in the SOPE dataset, our framework is evaluated on four diverse benchmarks SOPE, ROPE, ObjaversePose, and HANDAL, spanning over 300 categories. It achieves state-of-the-art accuracy on seen categories while demonstrating remarkably strong zero-shot generalization to unseen real-world objects, establishing a new standard for open-set 6D understanding in robotics and embodied AI.
Tactile sensing remains far less understood in neuroscience and less effective in artificial systems compared to more mature modalities such as vision and language. We bridge these gaps by introducing a novel Encoder-Attender-Decoder (EAD) framework to systematically explore the space of task-optimized temporal neural networks trained on realistic tactile input sequences from a customized rodent whisker-array simulator. We identify convolutional recurrent neural networks (ConvRNNs) as superior encoders to purely feedforward and state-space architectures for tactile categorization. Crucially, these ConvRNN-encoder-based EAD models achieve neural representations closely matching rodent somatosensory cortex, saturating the explainable neural variability and revealing a clear linear relationship between supervised categorization performance and neural alignment. Furthermore, contrastive self-supervised ConvRNN-encoder-based EADs, trained with tactile-specific augmentations, match supervised neural fits, serving as an ethologically-relevant, label-free proxy. For neuroscience, our findings highlight nonlinear recurrent processing as important for general-purpose tactile representations in somatosensory cortex, providing the first quantitative characterization of the underlying inductive biases in this system. For embodied AI, our results emphasize the importance of recurrent EAD architectures to handle realistic tactile inputs, along with tailored self-supervised learning methods for achieving robust tactile perception with the same type of sensors animals use to sense in unstructured environments.
Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. This work explores how agents trained with imitation learning can learn robust representations from both optimal and suboptimal demonstrations when given access to constructive language feedback as a means to contextualise different modes of behaviour. We directly provide language feedback embeddings as part of the input sequence into a Transformer-based policy, and optionally complement the traditional next action prediction objective with auxiliary self-supervised learning objectives for feedback prediction. We test our approach on a range of embodied Vision-and-Language tasks in our custom BabyAI-XGen environment and show significant improvements in agents' compositional generalisation abilities and robustness, suggesting that our data-efficient method allows models to successfully convert suboptimal behaviour into learning opportunities. Overall, our results suggest that language feedback is a competitive and intuitive alternative to intermediate scalar rewards for language-specified embodied tasks.
Developing embodied agents capable of performing complex interactive tasks in real-world scenarios remains a fundamental challenge in embodied AI. Although recent advances in simulation platforms have greatly enhanced task diversity to train embodied Vision Language Models (VLMs), most platforms rely on simplified robot morphologies and bypass the stochastic nature of low-level execution, which limits their transferability to real-world robots. To address these issues, we present a physics-based simulation platform DualTHOR for complex dual-arm humanoid robots, built upon an extended version of AI2-THOR. Our simulator includes real-world robot assets, a task suite for dual-arm collaboration, and inverse kinematics solvers for humanoid robots. We also introduce a contingency mechanism that incorporates potential failures through physics-based low-level execution, bridging the gap to real-world scenarios. Our simulator enables a more comprehensive evaluation of the robustness and generalization of VLMs in household environments. Extensive evaluations reveal that current VLMs struggle with dual-arm coordination and exhibit limited robustness in realistic environments with contingencies, highlighting the importance of using our simulator to develop more capable VLMs for embodied tasks. The code is available at https://github.com/ds199895/DualTHOR.git.
Autonomous vehicles must react in milliseconds while reasoning about road geometry and traffic intent to navigate complex situations. We introduce NovaDrive, a single-branch vision-language architecture that processes front-camera images, HD-map tiles, LiDAR depth, and textual waypoints in a single branch. A lightweight, two-stage cross-attention block first aligns waypoint tokens with the HD map, then refines attention over fine-grained image and depth patches. Coupled with a novel smoothness loss that discourages abrupt steering and speed changes, this design eliminates the need for recurrent memory. We fine-tune the top 15 layers of an 11B LLaMA-3.2 vision-language backbone, enabling real-time inference. On the nuScenes / Waymo subset of the MD-NEX Outdoor benchmark, NovaDrive raises success rate to 84% (+4%), boosts path-efficiency (SPL) to 0.66 (+0.11), and reduces collision frequency from 2.6% to 1.2% (-1.4%) relative to the previous state-of-the-art. Our ablations confirm that waypoint tokens, partial VLM fine-tuning, and the cross-attention fusion each contribute the most to these gains. Beyond safety, NovaDrive's shorter routes (resulting from the novel smoothness loss) translate to lower fuel or battery usage, pointing toward leaner, more easily updated driving stacks. NovaDrive can be extended to other embodied-AI domains as well.
With the growing deployment of Vision-Language-Action (VLA) models in real-world embodied AI systems, their increasing vulnerability to backdoor attacks poses a serious safety threat. A backdoored VLA agent can be covertly triggered by a pre-injected backdoor to execute adversarial actions, potentially causing system failures or even physical harm. Although backdoor attacks on VLA models have been explored, prior work has focused only on untargeted attacks, leaving the more practically threatening scenario of targeted manipulation unexamined. In this paper, we study targeted backdoor attacks on VLA models and introduce TabVLA, a novel framework that enables such attacks via black-box fine-tuning. TabVLA explores two deployment-relevant inference-time threat models: input-stream editing and in-scene triggering. It formulates poisoned data generation as an optimization problem to improve attack effectivess. Experiments with OpenVLA-7B on the LIBERO benchmark reveal that the vision channel is the principal attack surface: targeted backdoors succeed with minimal poisoning, remain robust across variations in trigger design, and are degraded only by positional mismatches between fine-tuning and inference triggers. We also investigate a potential detection-based defense against TabVLA, which reconstructs latent visual triggers from the input stream to flag activation-conditioned backdoor samples. Our work highlights the vulnerability of VLA models to targeted backdoor manipulation and underscores the need for more advanced defenses.
Good form is the difference between strength and strain, yet for the fast-growing community of at-home fitness enthusiasts, expert feedback is often out of reach. FormCoach transforms a simple camera into an always-on, interactive AI training partner, capable of spotting subtle form errors and delivering tailored corrections in real time, leveraging vision-language models (VLMs). We showcase this capability through a web interface and benchmark state-of-the-art VLMs on a dataset of 1,700 expert-annotated user-reference video pairs spanning 22 strength and mobility exercises. To accelerate research in AI-driven coaching, we release both the dataset and an automated, rubric-based evaluation pipeline, enabling standardized comparison across models. Our benchmarks reveal substantial gaps compared to human-level coaching, underscoring both the challenges and opportunities in integrating nuanced, context-aware movement analysis into interactive AI systems. By framing form correction as a collaborative and creative process between humans and machines, FormCoach opens a new frontier in embodied AI.
Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are critical for embodied AI, where agents must act under uncertainty and delayed perception. We introduce FOGMACHINE , an open-source framework that fuses DSGs with discrete-event simulation to model object dynamics, agent observations, and interactions at scale. This setup enables the study of uncertainty propagation, planning under limited perception, and emergent multi-agent behavior. Experiments in urban scenarios illustrate realistic temporal and spatial patterns while revealing the challenges of belief estimation under sparse observations. By combining structured representations with efficient simulation, FOGMACHINE establishes an effective tool for benchmarking, model training, and advancing embodied AI in complex, uncertain environments.
Estimating an object's 6D pose, size, and shape from visual input is a fundamental problem in computer vision, with critical applications in robotic grasping and manipulation. Existing methods either rely on object-specific priors such as CAD models or templates, or suffer from limited generalization across categories due to pose-shape entanglement and multi-stage pipelines. In this work, we propose a unified, category-agnostic framework that simultaneously predicts 6D pose, size, and dense shape from a single RGB-D image, without requiring templates, CAD models, or category labels at test time. Our model fuses dense 2D features from vision foundation models with partial 3D point clouds using a Transformer encoder enhanced by a Mixture-of-Experts, and employs parallel decoders for pose-size estimation and shape reconstruction, achieving real-time inference at 28 FPS. Trained solely on synthetic data from 149 categories in the SOPE dataset, our framework is evaluated on four diverse benchmarks SOPE, ROPE, ObjaversePose, and HANDAL, spanning over 300 categories. It achieves state-of-the-art accuracy on seen categories while demonstrating remarkably strong zero-shot generalization to unseen real-world objects, establishing a new standard for open-set 6D understanding in robotics and embodied AI.
Tactile sensing remains far less understood in neuroscience and less effective in artificial systems compared to more mature modalities such as vision and language. We bridge these gaps by introducing a novel Encoder-Attender-Decoder (EAD) framework to systematically explore the space of task-optimized temporal neural networks trained on realistic tactile input sequences from a customized rodent whisker-array simulator. We identify convolutional recurrent neural networks (ConvRNNs) as superior encoders to purely feedforward and state-space architectures for tactile categorization. Crucially, these ConvRNN-encoder-based EAD models achieve neural representations closely matching rodent somatosensory cortex, saturating the explainable neural variability and revealing a clear linear relationship between supervised categorization performance and neural alignment. Furthermore, contrastive self-supervised ConvRNN-encoder-based EADs, trained with tactile-specific augmentations, match supervised neural fits, serving as an ethologically-relevant, label-free proxy. For neuroscience, our findings highlight nonlinear recurrent processing as important for general-purpose tactile representations in somatosensory cortex, providing the first quantitative characterization of the underlying inductive biases in this system. For embodied AI, our results emphasize the importance of recurrent EAD architectures to handle realistic tactile inputs, along with tailored self-supervised learning methods for achieving robust tactile perception with the same type of sensors animals use to sense in unstructured environments.
Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating errors and inefficiencies. While reinforcement learning offers one alternative, the associated exploration typically results in sacrificing data efficiency. This work explores how agents trained with imitation learning can learn robust representations from both optimal and suboptimal demonstrations when given access to constructive language feedback as a means to contextualise different modes of behaviour. We directly provide language feedback embeddings as part of the input sequence into a Transformer-based policy, and optionally complement the traditional next action prediction objective with auxiliary self-supervised learning objectives for feedback prediction. We test our approach on a range of embodied Vision-and-Language tasks in our custom BabyAI-XGen environment and show significant improvements in agents' compositional generalisation abilities and robustness, suggesting that our data-efficient method allows models to successfully convert suboptimal behaviour into learning opportunities. Overall, our results suggest that language feedback is a competitive and intuitive alternative to intermediate scalar rewards for language-specified embodied tasks.
Developing embodied agents capable of performing complex interactive tasks in real-world scenarios remains a fundamental challenge in embodied AI. Although recent advances in simulation platforms have greatly enhanced task diversity to train embodied Vision Language Models (VLMs), most platforms rely on simplified robot morphologies and bypass the stochastic nature of low-level execution, which limits their transferability to real-world robots. To address these issues, we present a physics-based simulation platform DualTHOR for complex dual-arm humanoid robots, built upon an extended version of AI2-THOR. Our simulator includes real-world robot assets, a task suite for dual-arm collaboration, and inverse kinematics solvers for humanoid robots. We also introduce a contingency mechanism that incorporates potential failures through physics-based low-level execution, bridging the gap to real-world scenarios. Our simulator enables a more comprehensive evaluation of the robustness and generalization of VLMs in household environments. Extensive evaluations reveal that current VLMs struggle with dual-arm coordination and exhibit limited robustness in realistic environments with contingencies, highlighting the importance of using our simulator to develop more capable VLMs for embodied tasks. The code is available at https://github.com/ds199895/DualTHOR.git.
Autonomous vehicles must react in milliseconds while reasoning about road geometry and traffic intent to navigate complex situations. We introduce NovaDrive, a single-branch vision-language architecture that processes front-camera images, HD-map tiles, LiDAR depth, and textual waypoints in a single branch. A lightweight, two-stage cross-attention block first aligns waypoint tokens with the HD map, then refines attention over fine-grained image and depth patches. Coupled with a novel smoothness loss that discourages abrupt steering and speed changes, this design eliminates the need for recurrent memory. We fine-tune the top 15 layers of an 11B LLaMA-3.2 vision-language backbone, enabling real-time inference. On the nuScenes / Waymo subset of the MD-NEX Outdoor benchmark, NovaDrive raises success rate to 84% (+4%), boosts path-efficiency (SPL) to 0.66 (+0.11), and reduces collision frequency from 2.6% to 1.2% (-1.4%) relative to the previous state-of-the-art. Our ablations confirm that waypoint tokens, partial VLM fine-tuning, and the cross-attention fusion each contribute the most to these gains. Beyond safety, NovaDrive's shorter routes (resulting from the novel smoothness loss) translate to lower fuel or battery usage, pointing toward leaner, more easily updated driving stacks. NovaDrive can be extended to other embodied-AI domains as well.
With the growing deployment of Vision-Language-Action (VLA) models in real-world embodied AI systems, their increasing vulnerability to backdoor attacks poses a serious safety threat. A backdoored VLA agent can be covertly triggered by a pre-injected backdoor to execute adversarial actions, potentially causing system failures or even physical harm. Although backdoor attacks on VLA models have been explored, prior work has focused only on untargeted attacks, leaving the more practically threatening scenario of targeted manipulation unexamined. In this paper, we study targeted backdoor attacks on VLA models and introduce TabVLA, a novel framework that enables such attacks via black-box fine-tuning. TabVLA explores two deployment-relevant inference-time threat models: input-stream editing and in-scene triggering. It formulates poisoned data generation as an optimization problem to improve attack effectivess. Experiments with OpenVLA-7B on the LIBERO benchmark reveal that the vision channel is the principal attack surface: targeted backdoors succeed with minimal poisoning, remain robust across variations in trigger design, and are degraded only by positional mismatches between fine-tuning and inference triggers. We also investigate a potential detection-based defense against TabVLA, which reconstructs latent visual triggers from the input stream to flag activation-conditioned backdoor samples. Our work highlights the vulnerability of VLA models to targeted backdoor manipulation and underscores the need for more advanced defenses.
Good form is the difference between strength and strain, yet for the fast-growing community of at-home fitness enthusiasts, expert feedback is often out of reach. FormCoach transforms a simple camera into an always-on, interactive AI training partner, capable of spotting subtle form errors and delivering tailored corrections in real time, leveraging vision-language models (VLMs). We showcase this capability through a web interface and benchmark state-of-the-art VLMs on a dataset of 1,700 expert-annotated user-reference video pairs spanning 22 strength and mobility exercises. To accelerate research in AI-driven coaching, we release both the dataset and an automated, rubric-based evaluation pipeline, enabling standardized comparison across models. Our benchmarks reveal substantial gaps compared to human-level coaching, underscoring both the challenges and opportunities in integrating nuanced, context-aware movement analysis into interactive AI systems. By framing form correction as a collaborative and creative process between humans and machines, FormCoach opens a new frontier in embodied AI.
We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation stack we catalogue recurrent modalities including flip-flop, plan churn, perseveration loops, paralysis and hypervigilance, futile search, belief incoherence, tie break thrashing, corridor thrashing, optimality compulsion, metric mismatch, policy oscillation, and limited-visibility variants. For each we give lightweight online detectors and reusable escape policies (short commitments, a margin to switch, smoothing, principled arbitration). We then show that durable phobic avoidance can persist even under full visibility when learned aversive costs dominate local choice, producing long detours despite globally safe routes. Using First/Second/Third Law as engineering shorthand for safety latency, command compliance, and resource efficiency, we argue that local fixes are insufficient; global failures can remain. To surface them, we propose genetic-programming based destructive testing that evolves worlds and perturbations to maximize law pressure and neurosis scores, yielding adversarial curricula and counterfactual traces that expose where architectural revision, not merely symptom-level patches, is required.
We present a framework for characterizing neurosis in embodied AI: behaviors that are internally coherent yet misaligned with reality, arising from interactions among planning, uncertainty handling, and aversive memory. In a grid navigation stack we catalogue recurrent modalities including flip-flop, plan churn, perseveration loops, paralysis and hypervigilance, futile search, belief incoherence, tie break thrashing, corridor thrashing, optimality compulsion, metric mismatch, policy oscillation, and limited-visibility variants. For each we give lightweight online detectors and reusable escape policies (short commitments, a margin to switch, smoothing, principled arbitration). We then show that durable phobic avoidance can persist even under full visibility when learned aversive costs dominate local choice, producing long detours despite globally safe routes. Using First/Second/Third Law as engineering shorthand for safety latency, command compliance, and resource efficiency, we argue that local fixes are insufficient; global failures can remain. To surface them, we propose genetic-programming based destructive testing that evolves worlds and perturbations to maximize law pressure and neurosis scores, yielding adversarial curricula and counterfactual traces that expose where architectural revision, not merely symptom-level patches, is required.
In the approximately century-long journey of robotics, humanoid robots made their debut around six decades ago. While current humanoids bear human-like appearances, none have embodied true humaneness, remaining distant from achieving human-like to human-level intelligence. The rapid recent advancements in generative AI and (multimodal) large language models have further reignited and escalated interest in humanoids towards real-time, interactive, and multimodal designs and applications, such as fostering humanoid workers, advisers, educators, medical professionals, caregivers, and receptionists. These unveil boundless opportunities of transforming 1) AI robotics into a research era of humanoid AI, and 2) AI robots into new-generation humanoid AI robots (AI humanoids). Our unique and comprehensive review of about 30 reported humanoids discloses a systematic terminology and a paradigmatic landscape of human-looking to human-like and human-level humanoids. It inspires comprehensive new perspectives and directions of humanoid AI as an area: transitioning from human-looking to humane humanoids, humanizing humanoids with functional and nonfunctional specifications, and cultivating technical and actionable advances of AI humanoids. Humanoid AI and AI humanoids nurture symbiotic advancements and future opportunities of synthesizing and transforming humanity modeling and conventional, generative to human-level AI into humanoid robotics.
This survey provides a comprehensive overview of recent advances in multimodal alignment and fusion within the field of machine learning, driven by the increasing availability and diversity of data modalities such as text, images, audio, and video. Unlike previous surveys that often focus on specific modalities or limited fusion strategies, our work presents a structure-centric and method-driven framework that emphasizes generalizable techniques. We systematically categorize and analyze key approaches to alignment and fusion through both structural perspectives -- data-level, feature-level, and output-level fusion -- and methodological paradigms -- including statistical, kernel-based, graphical, generative, contrastive, attention-based, and large language model (LLM)-based methods, drawing insights from an extensive review of over 260 relevant studies. Furthermore, this survey highlights critical challenges such as cross-modal misalignment, computational bottlenecks, data quality issues, and the modality gap, along with recent efforts to address them. Applications ranging from social media analysis and medical imaging to emotion recognition and embodied AI are explored to illustrate the real-world impact of robust multimodal systems. The insights provided aim to guide future research toward optimizing multimodal learning systems for improved scalability, robustness, and generalizability across diverse domains.
This survey provides a comprehensive overview of recent advances in multimodal alignment and fusion within the field of machine learning, driven by the increasing availability and diversity of data modalities such as text, images, audio, and video. Unlike previous surveys that often focus on specific modalities or limited fusion strategies, our work presents a structure-centric and method-driven framework that emphasizes generalizable techniques. We systematically categorize and analyze key approaches to alignment and fusion through both structural perspectives -- data-level, feature-level, and output-level fusion -- and methodological paradigms -- including statistical, kernel-based, graphical, generative, contrastive, attention-based, and large language model (LLM)-based methods, drawing insights from an extensive review of over 260 relevant studies. Furthermore, this survey highlights critical challenges such as cross-modal misalignment, computational bottlenecks, data quality issues, and the modality gap, along with recent efforts to address them. Applications ranging from social media analysis and medical imaging to emotion recognition and embodied AI are explored to illustrate the real-world impact of robust multimodal systems. The insights provided aim to guide future research toward optimizing multimodal learning systems for improved scalability, robustness, and generalizability across diverse domains.
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysToolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. It assesses capabilities across three distinct difficulty levels: (1) Tool Recognition: Requiring the recognition of a tool's primary function. (2) Tool Understanding: Testing the ability to grasp the underlying principles of a tool's operation. (3) Tool Creation: Challenging the model to fashion a new tool from surrounding objects when conventional options are unavailable. Our comprehensive evaluation of 32 MLLMs-spanning proprietary, open-source, specialized embodied, and backbones in VLAs-reveals a significant deficiency in tool understanding. Furthermore, we provide an in-depth analysis and propose preliminary solutions. Code and dataset are publicly available.
Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are critical for embodied AI, where agents must act under uncertainty and delayed perception. We introduce FOGMACHINE , an open-source framework that fuses DSGs with discrete-event simulation to model object dynamics, agent observations, and interactions at scale. This setup enables the study of uncertainty propagation, planning under limited perception, and emergent multi-agent behavior. Experiments in urban scenarios illustrate realistic temporal and spatial patterns while revealing the challenges of belief estimation under sparse observations. By combining structured representations with efficient simulation, FOGMACHINE establishes an effective tool for benchmarking, model training, and advancing embodied AI in complex, uncertain environments.
Recent advances in vision-language-action (VLA) models have greatly improved embodied AI, enabling robots to follow natural language instructions and perform diverse tasks. However, their reliance on uncurated training datasets raises serious security concerns. Existing backdoor attacks on VLAs mostly assume white-box access and result in task failures instead of enforcing specific actions. In this work, we reveal a more practical threat: attackers can manipulate VLAs by simply injecting physical objects as triggers into the training dataset. We propose goal-oriented backdoor attacks (GoBA), where the VLA behaves normally in the absence of physical triggers but executes predefined and goal-oriented actions in the presence of physical triggers. Specifically, based on a popular VLA benchmark LIBERO, we introduce BadLIBERO that incorporates diverse physical triggers and goal-oriented backdoor actions. In addition, we propose a three-level evaluation that categorizes the victim VLA's actions under GoBA into three states: nothing to do, try to do, and success to do. Experiments show that GoBA enables the victim VLA to successfully achieve the backdoor goal in 97 percentage of inputs when the physical trigger is present, while causing zero performance degradation on clean inputs. Finally, by investigating factors related to GoBA, we find that the action trajectory and trigger color significantly influence attack performance, while trigger size has surprisingly little effect. The code and BadLIBERO dataset are accessible via the project page at https://goba-attack.github.io/.
Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for Autonomous Driving, Embodied AI and General Artificial Intelligence. Existing spatial-temporal benchmarks mainly focus on egocentric perspective reasoning with images/video context, or geographic perspective reasoning with graphics context (eg. a map), thus fail to assess VLMs' geographic spatial-temporal intelligence with both images/video and graphics context, which is important for areas like traffic management and emergency response. To address the gaps, we introduce Geo-Temporal Reasoning benchmark (GTR-Bench), a novel challenge for geographic temporal reasoning of moving targets in a large-scale camera network. GTR-Bench is more challenging as it requires multiple perspective switches between maps and videos, joint reasoning across multiple videos with non-overlapping fields of view, and inference over spatial-temporal regions that are unobserved by any video context. Evaluations of more than 10 popular VLMs on GTR-Bench demonstrate that even the best proprietary model, Gemini-2.5-Pro (34.9%), significantly lags behind human performance (78.61%) on geo-temporal reasoning. Moreover, our comprehensive analysis on GTR-Bench reveals three primary deficiencies of current models for geo-temporal reasoning. (1) VLMs' reasoning is impaired by an imbalanced utilization of spatial-temporal context. (2) VLMs are weak in temporal forecasting, which leads to worse performance on temporal-emphasized tasks than on spatial-emphasized tasks. (3) VLMs lack the proficiency to comprehend or align the map data with multi-view video inputs. We believe GTR-Bench offers valuable insights and opens up new opportunities for research and applications in spatial-temporal intelligence. Benchmark and code will be released at https://github.com/X-Luffy/GTR-Bench.
Dynamic Scene Graphs (DSGs) provide a structured representation of hierarchical, interconnected environments, but current approaches struggle to capture stochastic dynamics, partial observability, and multi-agent activity. These aspects are critical for embodied AI, where agents must act under uncertainty and delayed perception. We introduce FOGMACHINE , an open-source framework that fuses DSGs with discrete-event simulation to model object dynamics, agent observations, and interactions at scale. This setup enables the study of uncertainty propagation, planning under limited perception, and emergent multi-agent behavior. Experiments in urban scenarios illustrate realistic temporal and spatial patterns while revealing the challenges of belief estimation under sparse observations. By combining structured representations with efficient simulation, FOGMACHINE establishes an effective tool for benchmarking, model training, and advancing embodied AI in complex, uncertain environments.
The ability to use, understand, and create tools is a hallmark of human intelligence, enabling sophisticated interaction with the physical world. For any general-purpose intelligent agent to achieve true versatility, it must also master these fundamental skills. While modern Multimodal Large Language Models (MLLMs) leverage their extensive common knowledge for high-level planning in embodied AI and in downstream Vision-Language-Action (VLA) models, the extent of their true understanding of physical tools remains unquantified. To bridge this gap, we present PhysToolBench, the first benchmark dedicated to evaluating the comprehension of physical tools by MLLMs. Our benchmark is structured as a Visual Question Answering (VQA) dataset comprising over 1,000 image-text pairs. It assesses capabilities across three distinct difficulty levels: (1) Tool Recognition: Requiring the recognition of a tool's primary function. (2) Tool Understanding: Testing the ability to grasp the underlying principles of a tool's operation. (3) Tool Creation: Challenging the model to fashion a new tool from surrounding objects when conventional options are unavailable. Our comprehensive evaluation of 32 MLLMs-spanning proprietary, open-source, specialized embodied, and backbones in VLAs-reveals a significant deficiency in tool understanding. Furthermore, we provide an in-depth analysis and propose preliminary solutions. Code and dataset are publicly available.
Recent advances in vision-language-action (VLA) models have greatly improved embodied AI, enabling robots to follow natural language instructions and perform diverse tasks. However, their reliance on uncurated training datasets raises serious security concerns. Existing backdoor attacks on VLAs mostly assume white-box access and result in task failures instead of enforcing specific actions. In this work, we reveal a more practical threat: attackers can manipulate VLAs by simply injecting physical objects as triggers into the training dataset. We propose goal-oriented backdoor attacks (GoBA), where the VLA behaves normally in the absence of physical triggers but executes predefined and goal-oriented actions in the presence of physical triggers. Specifically, based on a popular VLA benchmark LIBERO, we introduce BadLIBERO that incorporates diverse physical triggers and goal-oriented backdoor actions. In addition, we propose a three-level evaluation that categorizes the victim VLA's actions under GoBA into three states: nothing to do, try to do, and success to do. Experiments show that GoBA enables the victim VLA to successfully achieve the backdoor goal in 97 percentage of inputs when the physical trigger is present, while causing zero performance degradation on clean inputs. Finally, by investigating factors related to GoBA, we find that the action trajectory and trigger color significantly influence attack performance, while trigger size has surprisingly little effect. The code and BadLIBERO dataset are accessible via the project page at https://goba-attack.github.io/.
Recently spatial-temporal intelligence of Visual-Language Models (VLMs) has attracted much attention due to its importance for Autonomous Driving, Embodied AI and General Artificial Intelligence. Existing spatial-temporal benchmarks mainly focus on egocentric perspective reasoning with images/video context, or geographic perspective reasoning with graphics context (eg. a map), thus fail to assess VLMs' geographic spatial-temporal intelligence with both images/video and graphics context, which is important for areas like traffic management and emergency response. To address the gaps, we introduce Geo-Temporal Reasoning benchmark (GTR-Bench), a novel challenge for geographic temporal reasoning of moving targets in a large-scale camera network. GTR-Bench is more challenging as it requires multiple perspective switches between maps and videos, joint reasoning across multiple videos with non-overlapping fields of view, and inference over spatial-temporal regions that are unobserved by any video context. Evaluations of more than 10 popular VLMs on GTR-Bench demonstrate that even the best proprietary model, Gemini-2.5-Pro (34.9%), significantly lags behind human performance (78.61%) on geo-temporal reasoning. Moreover, our comprehensive analysis on GTR-Bench reveals three primary deficiencies of current models for geo-temporal reasoning. (1) VLMs' reasoning is impaired by an imbalanced utilization of spatial-temporal context. (2) VLMs are weak in temporal forecasting, which leads to worse performance on temporal-emphasized tasks than on spatial-emphasized tasks. (3) VLMs lack the proficiency to comprehend or align the map data with multi-view video inputs. We believe GTR-Bench offers valuable insights and opens up new opportunities for research and applications in spatial-temporal intelligence. Benchmark and code will be released at https://github.com/X-Luffy/GTR-Bench.