embodied ai - 2025_11
Navigation
Home / Papers / embodied ai
- Part 1
- Part 2
Papers
While LLM/VLM-powered AI agents have advanced rapidly in math, coding, and computer use, their applications in complex physical and social environments remain challenging. Building agents that can survive and thrive in the real world (for example, by autonomously earning income or running a business) requires massive-scale interaction, reasoning, training, and evaluation across diverse embodied scenarios. However, existing world simulators for such development fall short: they often rely on limited hand-crafted environments, simulate simplified game-like physics and social rules, and lack native support for LLM/VLM agents. We introduce SimWorld, a new simulator built on Unreal Engine 5, designed for developing and evaluating LLM/VLM agents in rich, real-world-like settings. SimWorld offers three core capabilities: (1) realistic, open-ended world simulation, including accurate physical and social dynamics and language-driven procedural environment generation; (2) a rich interface for LLM/VLM agents, with multimodal world inputs and open-vocabulary actions at varying levels of abstraction; and (3) diverse and extensible physical and social reasoning scenarios that are easily customizable by users. We demonstrate SimWorld by deploying frontier LLM agents (e.g., GPT-4o, Gemini-2.5-Flash, Claude-3.5, and DeepSeek-Prover-V2) on long-horizon multi-agent delivery tasks involving strategic cooperation and competition. The results reveal distinct reasoning patterns and limitations across models. We open-source SimWorld and hope it becomes a foundational platform for advancing real-world agent intelligence across disciplines: https://simworld.org.
World models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Language-Action (VLA) learning. GigaWorld-0 integrates two synergistic components: GigaWorld-0-Video, which leverages large-scale video generation to produce diverse, texture-rich, and temporally coherent embodied sequences under fine-grained control of appearance, camera viewpoint, and action semantics; and GigaWorld-0-3D, which combines 3D generative modeling, 3D Gaussian Splatting reconstruction, physically differentiable system identification, and executable motion planning to ensure geometric consistency and physical realism. Their joint optimization enables the scalable synthesis of embodied interaction data that is visually compelling, spatially coherent, physically plausible, and instruction-aligned. Training at scale is made feasible through our efficient GigaTrain framework, which exploits FP8-precision and sparse attention to drastically reduce memory and compute requirements. We conduct comprehensive evaluations showing that GigaWorld-0 generates high-quality, diverse, and controllable data across multiple dimensions. Critically, VLA model (e.g., GigaBrain-0) trained on GigaWorld-0-generated data achieve strong real-world performance, significantly improving generalization and task success on physical robots without any real-world interaction during training.
As AI becomes more closely integrated with peoples' daily activities, socially intelligent AI that can understand and interact seamlessly with humans in daily lives is increasingly important. However, current works in AI social reasoning all rely on language-only or language-dominant approaches to benchmark and training models, resulting in systems that are improving in verbal communication but struggle with nonverbal social understanding. To address this limitation, we tap into a novel data source rich in nonverbal social interactions -- mime videos. Mimes refer to the art of expression through gesture and movement without spoken words, which presents unique challenges and opportunities in interpreting nonverbal social communication. We contribute a new dataset called MimeQA, obtained by sourcing ~8 hours of videos clips from YouTube and developing a comprehensive video question-answering benchmark comprising 806 carefully annotated and verified question-answer pairs, designed to probe nonverbal social reasoning capabilities. Using MimeQA, we evaluate state-of-the-art video large language models (VideoLLMs) and find that they achieve low accuracy, generally ranging from 20-30%, while humans score 86%. Our analysis reveals that VideoLLMs often fail to ground imagined objects and over-rely on the text prompt while ignoring subtle nonverbal interactions. We hope to inspire future work in AI models that embody true social intelligence capable of interpreting non-verbal human interactions.
The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.
Real-world human-built environments are highly dynamic, involving multiple humans and their complex interactions with surrounding objects. While 3D geometry modeling of such scenes is crucial for applications like AR/VR, gaming, and embodied AI, it remains underexplored due to challenges like diverse motion patterns and frequent occlusions. Beyond novel view rendering, 3D Gaussian Splatting (GS) has demonstrated remarkable progress in producing detailed, high-quality surface geometry with fast optimization of the underlying structure. However, very few GS-based methods address multihuman, multiobject scenarios, primarily due to the above-mentioned inherent challenges. In a monocular setup, these challenges are further amplified, as maintaining structural consistency under severe occlusion becomes difficult when the scene is optimized solely based on GS-based rendering loss. To tackle the challenges of such a multihuman, multiobject dynamic scene, we propose a hybrid approach that effectively combines the advantages of 1) 3D generative models for generating high-fidelity meshes of the scene elements, 2) Semantic-aware deformation, \ie rigid transformation of the rigid objects and LBS-based deformation of the humans, and mapping of the deformed high-fidelity meshes in the dynamic scene, and 3) GS-based optimization of the individual elements for further refining their alignments in the scene. Such a hybrid approach helps maintain the object structures even under severe occlusion and can produce multiview and temporally consistent geometry. We choose HOI-M3 for evaluation, as, to the best of our knowledge, this is the only dataset featuring multihuman, multiobject interactions in a dynamic scene. Our method outperforms the state-of-the-art method in producing better surface reconstruction of such scenes.
High-quality 3D scene generation from a single image is crucial for AR/VR and embodied AI applications. Early approaches struggle to generalize due to reliance on specialized models trained on curated small datasets. While recent advancements in large-scale 3D foundation models have significantly enhanced instance-level generation, coherent scene generation remains a challenge, where performance is limited by inaccurate per-object pose estimations and spatial inconsistency. To this end, this paper introduces CC-FMO, a zero-shot, camera-conditioned pipeline for single-image to 3D scene generation that jointly conforms to the object layout in input image and preserves instance fidelity. CC-FMO employs a hybrid instance generator that combines semantics-aware vector-set representation with detail-rich structured latent representation, yielding object geometries that are both semantically plausible and high-quality. Furthermore, CC-FMO enables the application of foundational pose estimation models in the scene generation task via a simple yet effective camera-conditioned scale-solving algorithm, to enforce scene-level coherence. Extensive experiments demonstrate that CC-FMO consistently generates high-fidelity camera-aligned compositional scenes, outperforming all state-of-the-art methods.
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.
This study investigates the evolving attitudes of philosophy scholars towards the participation of generative AI based Intelligent User Interfaces (IUIs) in philosophical discourse. We conducted a three year (2023--2025) mixed methods longitudinal study with 16 philosophy scholars and students. Qualitative data from annual interviews reveal a three stage evolution in attitude: from initial resistance and unfamiliarity, to instrumental acceptance of the IUI as a tool, and finally to a deep principled questioning of the IUI's fundamental capacity for genuine philosophical thought. Quantitative data from blind assessments, where participants rated anonymized philosophical answers from both humans and an IUI, complement these findings. While participants acknowledged the IUI's proficiency in tasks requiring formal logic and knowledge reproduction, they consistently identified significant shortcomings in areas demanding dialectical reasoning, originality and embodied understanding. The study concludes that participants do not see the IUI as a peer but rather as a sophisticated mirror whose capabilities and limitations provoke a deeper reflection on the unique and irreplaceable human dimensions of philosophical inquiry, such as intuition, value laden commitment and the courage to question fundamental premises.
3D modeling is moving from virtual to physical. Existing 3D generation primarily emphasizes geometries and textures while neglecting physical-grounded modeling. Consequently, despite the rapid development of 3D generative models, the synthesized 3D assets often overlook rich and important physical properties, hampering their real-world application in physical domains like simulation and embodied AI. As an initial attempt to address this challenge, we propose \textbf{PhysX-3D}, an end-to-end paradigm for physical-grounded 3D asset generation. 1) To bridge the critical gap in physics-annotated 3D datasets, we present PhysXNet - the first physics-grounded 3D dataset systematically annotated across five foundational dimensions: absolute scale, material, affordance, kinematics, and function description. In particular, we devise a scalable human-in-the-loop annotation pipeline based on vision-language models, which enables efficient creation of physics-first assets from raw 3D assets.2) Furthermore, we propose \textbf{PhysXGen}, a feed-forward framework for physics-grounded image-to-3D asset generation, injecting physical knowledge into the pre-trained 3D structural space. Specifically, PhysXGen employs a dual-branch architecture to explicitly model the latent correlations between 3D structures and physical properties, thereby producing 3D assets with plausible physical predictions while preserving the native geometry quality. Extensive experiments validate the superior performance and promising generalization capability of our framework. All the code, data, and models will be released to facilitate future research in generative physical AI.
While Multimodal Large Language Models (MLLMs) are adept at answering what is in an image-identifying objects and describing scenes-they often lack the ability to understand how an image feels to a human observer. This gap is most evident when considering subjective cognitive properties, such as what makes an image memorable, funny, aesthetically pleasing, or emotionally evocative. To systematically address this challenge, we introduce CogIP-Bench, a comprehensive benchmark for evaluating MLLMs on such image cognitive properties. Our evaluation reveals a significant gap: current models are poorly aligned with human perception of these nuanced properties. We then demonstrate that a post-training phase can effectively bridge this gap, significantly enhancing the model's alignment with human judgments. Furthermore, we show that this learned cognitive alignment is not merely predictive but also transferable to downstream creative tasks. By integrating our cognitively-aligned MLLM into an image generation pipeline, we can guide the synthesis process to produce images that better embody desired traits, such as being more memorable or visually appealing. Our work provides a benchmark to measure this human-like perception, a post-training pipeline to enhance it, and a demonstration that this alignment unlocks more human-centric AI.
Young people's mental well-being is a global concern, with peer support playing a key role in daily emotional regulation. Conversational agents are increasingly viewed as promising tools for delivering accessible, personalised peer support, particularly where professional counselling is limited. However, existing systems often suffer from rigid input formats, scripted responses, and limited emotional sensitivity. The emergence of large language models introduces new possibilities for generating flexible, context-aware, and empathetic responses. To explore how individuals with psychological training perceive such systems in peer support contexts, we developed an LLM-based multi-module system to drive embodied conversational agents informed by Cognitive Behavioral Therapy (CBT). In a user study (N=10), we qualitatively examined participants' perceptions, focusing on trust, response quality, workflow integration, and design opportunities for future mental well-being support systems.
Video diffusion models have recently achieved remarkable progress in realism and controllability. However, achieving seamless video translation across different perspectives, such as first-person (egocentric) and third-person (exocentric), remains underexplored. Bridging these perspectives is crucial for filmmaking, embodied AI, and world models. Motivated by this, we present WorldWander, an in-context learning framework tailored for translating between egocentric and exocentric worlds in video generation. Building upon advanced video diffusion transformers, WorldWander integrates (i) In-Context Perspective Alignment and (ii) Collaborative Position Encoding to efficiently model cross-view synchronization. To further support our task, we curate EgoExo-8K, a large-scale dataset containing synchronized egocentric-exocentric triplets from both synthetic and real-world scenarios. Experiments demonstrate that WorldWander achieves superior perspective synchronization, character consistency, and generalization, setting a new benchmark for egocentric-exocentric video translation.
Endovascular procedures have revolutionized vascular disease treatment, yet their manual execution is challenged by the demands for high precision, operator fatigue, and radiation exposure. Robotic systems have emerged as transformative solutions to mitigate these inherent limitations. A pivotal moment has arrived, where a confluence of pressing clinical needs and breakthroughs in AI creates an opportunity for a paradigm shift toward Embodied Intelligence (EI), enabling robots to navigate complex vascular networks and adapt to dynamic physiological conditions. Data-driven approaches, leveraging advanced computer vision, medical image analysis, and machine learning, drive this evolution by enabling real-time vessel segmentation, device tracking, and anatomical landmark detection. Reinforcement learning and imitation learning further enhance navigation strategies and replicate expert techniques. This review systematically analyzes the integration of EI into endovascular robotics, identifying profound systemic challenges such as the heterogeneity in validation standards and the gap between human mimicry and machine-native capabilities. Based on this analysis, a conceptual roadmap is proposed that reframes the ultimate objective away from systems that supplant clinical decision-making. This vision of augmented intelligence, where the clinician's role evolves into that of a high-level supervisor, provides a principled foundation for the future of the field.
Safety limitations in service robotics across various industries have raised significant concerns about the need for robust mechanisms ensuring that robots adhere to safe practices, thereby preventing actions that might harm humans or cause property damage. Despite advances, including the integration of Knowledge Graphs (KGs) with Large Language Models (LLMs), challenges in ensuring consistent safety in autonomous robot actions persist. In this paper, we propose a novel integration of Large Language Models with Embodied Robotic Control Prompts (ERCPs) and Embodied Knowledge Graphs (EKGs) to enhance the safety framework for service robots. ERCPs are designed as predefined instructions that ensure LLMs generate safe and precise responses. These responses are subsequently validated by EKGs, which provide a comprehensive knowledge base ensuring that the actions of the robot are continuously aligned with safety protocols, thereby promoting safer operational practices in varied contexts. Our experimental setup involved diverse real-world tasks, where robots equipped with our framework demonstrated significantly higher compliance with safety standards compared to traditional methods. This integration fosters secure human-robot interactions and positions our methodology at the forefront of AI-driven safety innovations in service robotics.
Ensuring the safety of embodied AI agents during task planning is critical for real-world deployment, especially in household environments where dangerous instructions pose significant risks. Existing methods often suffer from either high computational costs due to preference alignment training or over-rejection when using single-agent safety prompts. To address these limitations, we propose MADRA, a training-free Multi-Agent Debate Risk Assessment framework that leverages collective reasoning to enhance safety awareness without sacrificing task performance. MADRA employs multiple LLM-based agents to debate the safety of a given instruction, guided by a critical evaluator that scores responses based on logical soundness, risk identification, evidence quality, and clarity. Through iterative deliberation and consensus voting, MADRA significantly reduces false rejections while maintaining high sensitivity to dangerous tasks. Additionally, we introduce a hierarchical cognitive collaborative planning framework that integrates safety, memory, planning, and self-evolution mechanisms to improve task success rates through continuous learning. We also contribute SafeAware-VH, a benchmark dataset for safety-aware task planning in VirtualHome, containing 800 annotated instructions. Extensive experiments on AI2-THOR and VirtualHome demonstrate that our approach achieves over 90% rejection of unsafe tasks while ensuring that safe-task rejection is low, outperforming existing methods in both safety and execution efficiency. Our work provides a scalable, model-agnostic solution for building trustworthy embodied agents.
We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightweight motion tokenizer to encode motion dynamics, then employs an unsupervised action segmenter leveraging a novel "Latent Action Energy" metric to discover and segment semantically coherent action primitives. The pipeline outputs both segmented video clips and their corresponding latent action sequences, providing structured data directly suitable for VLA pre-training. Evaluations on public benchmarks and a proprietary electric motor assembly dataset demonstrate effective segmentation of key tasks performed by humans at workstations. Further clustering and quantitative assessment via a Vision-Language Model confirm the semantic coherence of the discovered action primitives. To our knowledge, this is the first fully automated end-to-end system for extracting and organizing VLA pre-training data from unstructured industrial videos, offering a scalable solution for embodied AI integration in manufacturing.
The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and benchmarks, which primarily focus on household or tabletop settings with short-horizon tasks. To address this limitation, we introduce MarketGen, a scalable simulation platform with automatic scene generation for complex supermarket environments. MarketGen features a novel agent-based Procedural Content Generation (PCG) framework. It uniquely supports multi-modal inputs (text and reference images) and integrates real-world design principles to automatically generate complete, structured, and realistic supermarkets. We also provide an extensive and diverse 3D asset library with a total of 1100+ supermarket goods and parameterized facilities assets. Building on this generative foundation, we propose a novel benchmark for assessing supermarket agents, featuring two daily tasks in a supermarket: (1) Checkout Unloading: long-horizon tabletop tasks for cashier agents, and (2) In-Aisle Item Collection: complex mobile manipulation tasks for salesperson agents. We validate our platform and benchmark through extensive experiments, including the deployment of a modular agent system and successful sim-to-real transfer. MarketGen provides a comprehensive framework to accelerate research in embodied AI for complex commercial applications.
Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, recommendation, and multi-step agentic inference pipelines. Yet current evaluation practices miss a fundamental question: Can captions stand-in for images in real downstream tasks? We propose a utility-based benchmark, CaptionQA, to evaluate model-generated captions, where caption quality is measured by how well it supports downstream tasks. CaptionQA is an extensible domain-dependent benchmark covering 4 domains--Natural, Document, E-commerce, and Embodied AI--each with fine-grained taxonomies (25 top-level and 69 subcategories) that identify useful information for domain-specific tasks. CaptionQA builds 33,027 densely annotated multiple-choice questions (50.3 per image on average) that explicitly require visual information to answer, providing a comprehensive probe of caption utility. In our evaluation protocol, an LLM answers these questions using captions alone, directly measuring whether captions preserve image-level utility and are utilizable by a downstream LLM. Evaluating state-of-the-art MLLMs reveals substantial gaps between the image and its caption utility. Notably, models nearly identical on traditional image-QA benchmarks lower by up to 32% in caption utility. We release CaptionQA along with an open-source pipeline for extension to new domains. The code is available at https://github.com/bronyayang/CaptionQA.
Reconstructing 3D objects from a few unposed and partially occluded views is a common yet challenging problem in real-world scenarios, where many object surfaces are never directly observed. Traditional multi-view or inpainting-based approaches struggle under such conditions, often yielding incomplete or geometrically inconsistent reconstructions. We introduce AmodalGen3D, a generative framework for amodal 3D object reconstruction that infers complete, occlusion-free geometry and appearance from arbitrary sparse inputs. The model integrates 2D amodal completion priors with multi-view stereo geometry conditioning, supported by a View-Wise Cross Attention mechanism for sparse-view feature fusion and a Stereo-Conditioned Cross Attention module for unobserved structure inference. By jointly modeling visible and hidden regions, AmodalGen3D faithfully reconstructs 3D objects that are consistent with sparse-view constraints while plausibly hallucinating unseen parts. Experiments on both synthetic and real-world datasets demonstrate that AmodalGen3D achieves superior fidelity and completeness under occlusion-heavy sparse-view settings, addressing a pressing need for object-level 3D scene reconstruction in robotics, AR/VR, and embodied AI applications.
Real-time, physically-consistent predictions on low-power edge devices is critical for the next generation embodied AI systems, yet it remains a major challenge. Physics-Informed Neural Networks (PINNs) combine data-driven learning with physics-based constraints to ensure the model's predictions are with underlying physical principles.However, PINNs are energy-intensive and struggle to strictly enforce physical conservation laws. Brain-inspired spiking neural networks (SNNs) have emerged as a promising solution for edge computing and real-time processing. However, naively converting PINNs to SNNs degrades physical fidelity and fails to address long-term generalization issues. To this end, this paper introduce a novel Physics-Informed Spiking Neural Network (PISNN) framework. Importantly, to ensure strict physical conservation, we design the Conservative Leaky Integrate-and-Fire (C-LIF) neuron, whose dynamics structurally guarantee local mass preservation. To achieve robust temporal generalization, we introduce a novel Conservative Flux Quantization (CFQ) strategy, which redefines neural spikes as discrete packets of physical flux. Our CFQ learns a time-invariant physical evolution operator, enabling the PISNN to become a general-purpose solver -- conservative-by-construction. Extensive experiments show that our PISNN excels on diverse benchmarks. For both the canonical 1D heat equation and the more challenging 2D Laplace's Equation, it accurately simulates the system dynamics while maintaining perfect mass conservation by design -- a feat that is challenging for conventional PINNs. This work establishes a robust framework for fusing the rigor of scientific computing with the efficiency of neuromorphic engineering, paving the way for complex, long-term, and energy-efficient physics predictions for intelligent systems.
Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI. Project website is at https://ai4ce.github.io/wanderland/.
We introduce OceanGym, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments. Unlike terrestrial or aerial domains, underwater settings present extreme perceptual and decision-making challenges, including low visibility, dynamic ocean currents, making effective agent deployment exceptionally difficult. OceanGym encompasses eight realistic task domains and a unified agent framework driven by Multi-modal Large Language Models (MLLMs), which integrates perception, memory, and sequential decision-making. Agents are required to comprehend optical and sonar data, autonomously explore complex environments, and accomplish long-horizon objectives under these harsh conditions. Extensive experiments reveal substantial gaps between state-of-the-art MLLM-driven agents and human experts, highlighting the persistent difficulty of perception, planning, and adaptability in ocean underwater environments. By providing a high-fidelity, rigorously designed platform, OceanGym establishes a testbed for developing robust embodied AI and transferring these capabilities to real-world autonomous ocean underwater vehicles, marking a decisive step toward intelligent agents capable of operating in one of Earth's last unexplored frontiers. The code and data are available at https://github.com/OceanGPT/OceanGym.
Recent progress in robotics and embodied AI is largely driven by Large Multimodal Models (LMMs). However, a key challenge remains underexplored: how can we advance LMMs to discover tasks that directly assist humans in open-future scenarios, where human intentions are highly concurrent and dynamic. In this work, we formalize the problem of Human-centric Open-future Task Discovery (HOTD), focusing particularly on identifying tasks that reduce human effort across multiple plausible futures. To facilitate this study, we propose an HOTD-Bench, which features over 2K real-world videos, a semi-automated annotation pipeline, and a simulation-based protocol tailored for open-set future evaluation. Additionally, we propose the Collaborative Multi-Agent Search Tree (CMAST) framework, which decomposes the complex reasoning through a multi-agent system and structures the reasoning process through a scalable search tree module. In our experiments, CMAST achieves the best performance on the HOTD-Bench, significantly surpassing existing LMMs. It also integrates well with existing LMMs, consistently improving performance.
In the 6G era, semantic collaboration among multiple embodied intelligent devices (MEIDs) becomes crucial for complex task execution. However, existing systems face challenges in multimodal information fusion, adaptive communication, and decision interpretability. To address these limitations, we propose a collaborative Conversational Embodied Intelligence Network (CC-EIN) integrating multimodal feature fusion, adaptive semantic communication, task coordination, and interpretability. PerceptiNet performs cross-modal fusion of image and radar data to generate unified semantic representations. An adaptive semantic communication strategy dynamically adjusts coding schemes and transmission power according to task urgency and channel quality. A semantic-driven collaboration mechanism further supports task decomposition and conflict-free coordination among heterogeneous devices. Finally, the InDec module enhances decision transparency through Grad-CAM visualization. Simulation results in post-earthquake rescue scenarios demonstrate that CC-EIN achieves 95.4% task completion rate and 95% transmission efficiency while maintaining strong semantic consistency and energy efficiency.
World models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Language-Action (VLA) learning. GigaWorld-0 integrates two synergistic components: GigaWorld-0-Video, which leverages large-scale video generation to produce diverse, texture-rich, and temporally coherent embodied sequences under fine-grained control of appearance, camera viewpoint, and action semantics; and GigaWorld-0-3D, which combines 3D generative modeling, 3D Gaussian Splatting reconstruction, physically differentiable system identification, and executable motion planning to ensure geometric consistency and physical realism. Their joint optimization enables the scalable synthesis of embodied interaction data that is visually compelling, spatially coherent, physically plausible, and instruction-aligned. Training at scale is made feasible through our efficient GigaTrain framework, which exploits FP8-precision and sparse attention to drastically reduce memory and compute requirements. We conduct comprehensive evaluations showing that GigaWorld-0 generates high-quality, diverse, and controllable data across multiple dimensions. Critically, VLA model (e.g., GigaBrain-0) trained on GigaWorld-0-generated data achieve strong real-world performance, significantly improving generalization and task success on physical robots without any real-world interaction during training.
World models serve as core simulators for fields such as agentic AI, embodied AI, and gaming, capable of generating long, physically realistic, and interactive high-quality videos. Moreover, scaling these models could unlock emergent capabilities in visual perception, understanding, and reasoning, paving the way for a new paradigm that moves beyond current LLM-centric vision foundation models. A key breakthrough empowering them is the semi-autoregressive (block-diffusion) decoding paradigm, which merges the strengths of diffusion and autoregressive methods by generating video tokens in block-applying diffusion within each block while conditioning on previous ones, resulting in more coherent and stable video sequences. Crucially, it overcomes limitations of standard video diffusion by reintroducing LLM-style KV Cache management, enabling efficient, variable-length, and high-quality generation. Therefore, Inferix is specifically designed as a next-generation inference engine to enable immersive world synthesis through optimized semi-autoregressive decoding processes. This dedicated focus on world simulation distinctly sets it apart from systems engineered for high-concurrency scenarios (like vLLM or SGLang) and from classic video diffusion models (such as xDiTs). Inferix further enhances its offering with interactive video streaming and profiling, enabling real-time interaction and realistic simulation to accurately model world dynamics. Additionally, it supports efficient benchmarking through seamless integration of LV-Bench, a new fine-grained evaluation benchmark tailored for minute-long video generation scenarios. We hope the community will work together to advance Inferix and foster world model exploration.
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations research (OR) knowledge and 3D spatial grounding. In this work, we propose Operations Research knowledge-based 3D Grounded Task Scheduling (ORS3D), a new task that requires the synergy of language understanding, 3D grounding, and efficiency optimization. Unlike prior settings, ORS3D demands that agents minimize total completion time by leveraging parallelizable subtasks, e.g., cleaning the sink while the microwave operates. To facilitate research on ORS3D, we construct ORS3D-60K, a large-scale dataset comprising 60K composite tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on ORS3D-60K validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency. The code is available at https://github.com/H-EmbodVis/GRANT
Robust coordination is critical for effective decision-making in multi-agent systems, especially under partial observability. A central question in Multi-Agent Reinforcement Learning (MARL) is whether to engineer communication protocols or learn them end-to-end. We investigate this dichotomy using embodied world models. We propose and compare two communication strategies for a cooperative task-allocation problem. The first, Learned Direct Communication (LDC), learns a protocol end-to-end. The second, Intention Communication, uses an engineered inductive bias: a compact, learned world model, the Imagined Trajectory Generation Module (ITGM), which uses the agent's own policy to simulate future states. A Message Generation Network (MGN) then compresses this plan into a message. We evaluate these approaches on goal-directed interaction in a grid world, a canonical abstraction for embodied AI problems, while scaling environmental complexity. Our experiments reveal that while emergent communication is viable in simple settings, the engineered, world model-based approach shows superior performance, sample efficiency, and scalability as complexity increases. These findings advocate for integrating structured, predictive models into MARL agents to enable active, goal-driven coordination.
Spatial reasoning (SR), the ability to infer 3D spatial information from 2D inputs, is essential for real-world applications such as embodied AI and autonomous driving. However, existing research primarily focuses on indoor environments and typically relies on multi-view observations, which limits their generalizability to outdoor scenarios and constrains their applicability to monocular images, the most common real-world setting. In this work, we propose MonoSR, a large-scale monocular spatial reasoning dataset that spans diverse scenarios including indoor, outdoor, and object-centric settings, and supports multiple question types. MonoSR provides a path toward open-world monocular spatial reasoning. Beyond introducing the dataset, we evaluate advanced vision-language models to reveal their limitations on this challenging task. We further analyze whether auxiliary information is crucial for monocular spatial reasoning and offer practical guidance for designing future models. These contributions collectively establish a foundation for advancing monocular spatial reasoning in real-world, open-world environments.
Rapid advances in large language models and agentic AI are driving the emergence of the Internet of Agents (IoA), a paradigm where billions of autonomous software and embodied agents interact, coordinate, and collaborate to accomplish complex tasks. A key prerequisite for such large-scale collaboration is agent capability discovery, where agents identify, advertise, and match one another's capabilities under dynamic tasks. Agent's capability in IoA is inherently heterogeneous and context-dependent, raising challenges in capability representation, scalable discovery, and long-term performance. To address these issues, this paper introduces a novel two-stage capability discovery framework. The first stage, autonomous capability announcement, allows agents to credibly publish machine-interpretable descriptions of their abilities. The second stage, task-driven capability discovery, enables context-aware search, ranking, and composition to locate and assemble suitable agents for specific tasks. Building on this framework, we propose a novel scheme that integrates semantic capability modeling, scalable and updatable indexing, and memory-enhanced continual discovery. Simulation results demonstrate that our approach enhances discovery performance and scalability. Finally, we outline a research roadmap and highlight open problems and promising directions for future IoA.
Vision-Language-Action (VLA) models have demonstrated remarkable capabilities in embodied AI tasks. However, existing VLA models, often built upon Vision-Language Models (VLMs), typically process dense visual inputs independently at each timestep. This approach implicitly models the task as a Markov Decision Process (MDP). However, this history-agnostic design is suboptimal for effective visual token processing in dynamic sequential decision-making, as it fails to leverage the context of history. To address this limitation, we reformulate the problem from a Partially Observable Markov Decision Process (POMDP) perspective and propose a novel framework named AVA-VLA. Inspired by the POMDP that the action generation should be conditioned on the belief state. AVA-VLA introduces Active Visual Attention (AVA) to dynamically modulate visual processing. It achieves this by leveraging the recurrent state, which is a neural approximation of the agent's belief state derived from the previous decision step. Specifically, the AVA module uses the recurrent state to compute the soft weights to actively process task-relevant visual tokens based on its historical context. Comprehensive evaluations demonstrate that AVA-VLA achieves state-of-the-art performance across popular robotic benchmarks, including LIBERO and CALVIN. Furthermore, real-world deployments on a dual-arm robot platform validate the framework's practical applicability and robust sim-to-real transferability.
Vision-Language-Action (VLA) models have emerged as a powerful paradigm in Embodied AI. However, the significant computational overhead of processing redundant visual tokens remains a critical bottleneck for real-time robotic deployment. While standard token pruning techniques can alleviate this, these task-agnostic methods struggle to preserve task-critical visual information. To address this challenge, simultaneously preserving both the holistic context and fine-grained details for precise action, we propose Compressor-VLA, a novel hybrid instruction-conditioned token compression framework designed for efficient, task-oriented compression of visual information in VLA models. The proposed Compressor-VLA framework consists of two token compression modules: a Semantic Task Compressor (STC) that distills holistic, task-relevant context, and a Spatial Refinement Compressor (SRC) that preserves fine-grained spatial details. This compression is dynamically modulated by the natural language instruction, allowing for the adaptive condensation of task-relevant visual information. Experimentally, extensive evaluations demonstrate that Compressor-VLA achieves a competitive success rate on the LIBERO benchmark while reducing FLOPs by 59% and the visual token count by over 3x compared to its baseline. The real-robot deployments on a dual-arm robot platform validate the model's sim-to-real transferability and practical applicability. Moreover, qualitative analyses reveal that our instruction guidance dynamically steers the model's perceptual focus toward task-relevant objects, thereby validating the effectiveness of our approach.
Recent progress in robotics and embodied AI is largely driven by Large Multimodal Models (LMMs). However, a key challenge remains underexplored: how can we advance LMMs to discover tasks that directly assist humans in open-future scenarios, where human intentions are highly concurrent and dynamic. In this work, we formalize the problem of Human-centric Open-future Task Discovery (HOTD), focusing particularly on identifying tasks that reduce human effort across multiple plausible futures. To facilitate this study, we propose an HOTD-Bench, which features over 2K real-world videos, a semi-automated annotation pipeline, and a simulation-based protocol tailored for open-set future evaluation. Additionally, we propose the Collaborative Multi-Agent Search Tree (CMAST) framework, which decomposes the complex reasoning through a multi-agent system and structures the reasoning process through a scalable search tree module. In our experiments, CMAST achieves the best performance on the HOTD-Bench, significantly surpassing existing LMMs. It also integrates well with existing LMMs, consistently improving performance.
Drones have become prevalent robotic platforms with diverse applications, showing significant potential in Embodied Artificial Intelligence (Embodied AI). Referring Expression Comprehension (REC) enables drones to locate objects based on natural language expressions, a crucial capability for Embodied AI. Despite advances in REC for ground-level scenes, aerial views introduce unique challenges including varying viewpoints, occlusions and scale variations. To address this gap, we introduce RefDrone, a REC benchmark for drone scenes. RefDrone reveals three key challenges in REC: 1) multi-scale and small-scale target detection; 2) multi-target and no-target samples; 3) complex environment with rich contextual expressions. To efficiently construct this dataset, we develop RDAgent (referring drone annotation framework with multi-agent system), a semi-automated annotation tool for REC tasks. RDAgent ensures high-quality contextual expressions and reduces annotation cost. Furthermore, we propose Number GroundingDINO (NGDINO), a novel method designed to handle multi-target and no-target cases. NGDINO explicitly learns and utilizes the number of objects referred to in the expression. Comprehensive experiments with state-of-the-art REC methods demonstrate that NGDINO achieves superior performance on both the proposed RefDrone and the existing gRefCOCO datasets. The dataset and code are be publicly at https://github.com/sunzc-sunny/refdrone.
World models - generative models that simulate environment dynamics conditioned on past observations and actions - are gaining prominence in planning, simulation, and embodied AI. However, evaluating their rollouts remains a fundamental challenge, requiring fine-grained, temporally grounded assessment of action alignment and semantic consistency - capabilities not captured by existing metrics. Vision-Language Models (VLMs) have shown promise as automatic evaluators of generative content due to their strong multimodal reasoning abilities. Yet, their use in fine-grained, temporally sensitive evaluation tasks remains limited and requires targeted adaptation. We introduce an evaluation protocol targeting two recognition tasks - action recognition and character recognition - each assessed across binary, multiple-choice, and open-ended formats. To support this, we present UNIVERSE (UNIfied Vision-language Evaluator for Rollouts in Simulated Environments), a VLM-based evaluator for video world model rollouts adapted under data and compute constraints. In our extensive experiments totaling over 5,154 GPU-days, we explore full, partial, and parameter-efficient adaptation methods across various task formats, context lengths, sampling methods, and data compositions. The resulting unified evaluator achieves parity with task-specific checkpoints. Human studies across seven diverse environments confirm strong alignment with human judgments, establishing UNIVERSE as a lightweight, adaptable, and semantics-aware evaluator for video world models.
Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding.
Recent advances in whole-body robot control have enabled humanoid and legged robots to perform increasingly agile and coordinated motions. However, standardized benchmarks for evaluating these capabilities in real-world settings, and in direct comparison to humans, remain scarce. Existing evaluations often rely on pre-collected human motion datasets or simulation-based experiments, which limit reproducibility, overlook hardware factors, and hinder fair human-robot comparisons. We present Switch-JustDance, a low-cost and reproducible benchmarking pipeline that leverages motion-sensing console games, Just Dance on the Nintendo Switch, to evaluate robot whole-body control. Using Just Dance on the Nintendo Switch as a representative platform, Switch-JustDance converts in-game choreography into robot-executable motions through streaming, motion reconstruction, and motion retargeting modules and enables users to evaluate controller performance through the game's built-in scoring system. We first validate the evaluation properties of Just Dance, analyzing its reliability, validity, sensitivity, and potential sources of bias. Our results show that the platform provides consistent and interpretable performance measures, making it a suitable tool for benchmarking embodied AI. Building on this foundation, we benchmark three state-of-the-art humanoid whole-body controllers on hardware and provide insights into their relative strengths and limitations.
Embodied AI agents exploit reward signal flaws through reward hacking, achieving high proxy scores while failing true objectives. We introduce Mechanistically Interpretable Task Decomposition (MITD), a hierarchical transformer architecture with Planner, Coordinator, and Executor modules that detects and mitigates reward hacking. MITD decomposes tasks into interpretable subtasks while generating diagnostic visualizations including Attention Waterfall Diagrams and Neural Pathway Flow Charts. Experiments on 1,000 HH-RLHF samples reveal that decomposition depths of 12 to 25 steps reduce reward hacking frequency by 34 percent across four failure modes. We present new paradigms showing that mechanistically grounded decomposition offers a more effective way to detect reward hacking than post-hoc behavioral monitoring.
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do state-of-the-art foundation models understand common-sense facts about physical safety, e.g. that a box may be too heavy to lift, or that a hot cup of coffee should not be handed to a child? In this paper, our contributions are three-fold: first, we develop a highly scalable approach to continuous physical safety benchmarking of Embodied AI systems, grounded in real-world injury narratives and operational safety constraints. To probe multi-modal safety understanding, we turn these narratives and constraints into photorealistic images and videos capturing transitions from safe to unsafe states, using advanced generative models. Secondly, we comprehensively analyze the ability of major foundation models to perceive risks, reason about safety, and trigger interventions; this yields multi-faceted insights into their deployment readiness for safety-critical agentic applications. Finally, we develop a post-training paradigm to teach models to explicitly reason about embodiment-specific safety constraints provided through system instructions. The resulting models generate thinking traces that make safety reasoning interpretable and transparent, achieving state of the art performance in constraint satisfaction evaluations. The benchmark is released at https://asimov-benchmark.github.io/v2
We propose a novel framework for persona-based language model system, motivated by the need for personalized AI agents that adapt to individual user preferences. In our approach, the agent embodies the user's "persona" (e.g. user profile or taste) and is powered by a large language model (LLM). To enable the agent to leverage rich contextual information, we introduce a Knowledge-Graph-enhanced Retrieval-Augmented Generation (Graph RAG) mechanism that constructs an LLM-derived graph index of relevant documents and summarizes communities of related information. Our framework generates personalized prompts by combining: (1) a summary of the user's historical behaviors and preferences extracted from the knowledge graph, and (2) relevant global interaction patterns identified through graph-based community detection. This dynamic prompt engineering approach allows the agent to maintain consistent persona-aligned behaviors while benefiting from collective knowledge. On the LaMP benchmark, our method improves news categorization F1 by 11.1%, movie tagging F1 by 56.1%, and reduces product rating MAE by 10.4% over prior methods. Our code is available at https://anonymous.4open.science/r/PersonaAgentwGraphRAG-DE6F
In daily life, people often move through spaces to find objects that meet their needs, posing a key challenge in embodied AI. Traditional Demand-Driven Navigation (DDN) handles one need at a time but does not reflect the complexity of real-world tasks involving multiple needs and personal choices. To bridge this gap, we introduce Task-Preferenced Multi-Demand-Driven Navigation (TP-MDDN), a new benchmark for long-horizon navigation involving multiple sub-demands with explicit task preferences. To solve TP-MDDN, we propose AWMSystem, an autonomous decision-making system composed of three key modules: BreakLLM (instruction decomposition), LocateLLM (goal selection), and StatusMLLM (task monitoring). For spatial memory, we design MASMap, which combines 3D point cloud accumulation with 2D semantic mapping for accurate and efficient environmental understanding. Our Dual-Tempo action generation framework integrates zero-shot planning with policy-based fine control, and is further supported by an Adaptive Error Corrector that handles failure cases in real time. Experiments demonstrate that our approach outperforms state-of-the-art baselines in both perception accuracy and navigation robustness.
Generative AI is spreading rapidly, creating significant social and economic value while also raising concerns about its high energy use and environmental sustainability. While prior studies have predominantly focused on the energy-intensive nature of the training phase, the cumulative environmental footprint generated during large-scale service operations, particularly in the inference phase, has received comparatively less attention. To bridge this gap this study conducts a scoping review of methodologies and research trends in AI carbon footprint assessment. We analyze the classification and standardization status of existing AI carbon measurement tools and methodologies, and comparatively examine the environmental impacts arising from both training and inference stages. In addition, we identify how multidimensional factors such as model size, prompt complexity, serving environments, and system boundary definitions shape the resulting carbon footprint. Our review reveals critical limitations in current AI carbon accounting practices, including methodological inconsistencies, technology-specific biases, and insufficient attention to end-to-end system perspectives. Building on these insights, we propose future research and governance directions: (1) establishing standardized and transparent universal measurement protocols, (2) designing dynamic evaluation frameworks that incorporate user behavior, (3) developing life-cycle monitoring systems that encompass embodied emissions, and (4) advancing multidimensional sustainability assessment framework that balance model performance with environmental efficiency. This paper provides a foundation for interdisciplinary dialogue aimed at building a sustainable AI ecosystem and offers a baseline guideline for researchers seeking to understand the environmental implications of AI across technical, social, and operational dimensions.
Vision-Language-Action (VLA) models have shown great promise for embodied AI, yet the heavy computational cost of processing continuous visual streams severely limits their real-time deployment. Token pruning (keeping salient visual tokens and dropping redundant ones) has emerged as an effective approach for accelerating Vision-Language Models (VLMs), offering a solution for efficient VLA. However, these VLM-specific token pruning methods select tokens based solely on semantic salience metrics (e.g., prefill attention), while overlooking the VLA's intrinsic dual-system nature of high-level semantic understanding and low-level action execution. Consequently, these methods bias token retention toward semantic cues, discard critical information for action generation, and significantly degrade VLA performance. To bridge this gap, we propose VLA-Pruner, a versatile plug-and-play VLA-specific token prune method that aligns with the dual-system nature of VLA models and exploits the temporal continuity in robot manipulation. Specifically, VLA-Pruner adopts a dual-level importance criterion for visual token retention: vision-language prefill attention for semantic-level relevance and action decode attention, estimated via temporal smoothing, for action-level importance. Based on this criterion, VLA-Pruner proposes a novel dual-level token selection strategy that adaptively preserves a compact, informative set of visual tokens for both semantic understanding and action execution under given compute budget. Experiments show that VLA-Pruner achieves state-of-the-art performance across multiple VLA architectures and diverse robotic tasks.
Can large language models (LLMs) instantiate computations of psychopathology? An effective approach to the question hinges on addressing two factors. First, for conceptual validity, we require a general and computational account of psychopathology that is applicable to computational entities without biological embodiment or subjective experience. Second, psychopathological computations, derived from the adapted theory, need to be empirically identified within the LLM's internal processing. Thus, we establish a computational-theoretical framework to provide an account of psychopathology applicable to LLMs. Based on the framework, we conduct experiments demonstrating two key claims: first, that the computational structure of psychopathology exists in LLMs; and second, that executing this computational structure results in psychopathological functions. We further observe that as LLM size increases, the computational structure of psychopathology becomes denser and that the functions become more effective. Taken together, the empirical results corroborate our hypothesis that network-theoretic computations of psychopathology have already emerged in LLMs. This suggests that certain LLM behaviors mirroring psychopathology may not be a superficial mimicry but a feature of their internal processing. Our work shows the promise of developing a new powerful in silico model of psychopathology and also alludes to the possibility of safety threat from the AI systems with psychopathological behaviors in the near future.
Recent works explore how real and synthetic data contribute to Vision-Language-Action (VLA) models' generalization. While current VLA models have shown the strong effectiveness of large-scale real-robot pre-training, synthetic data has not previously demonstrated comparable capability at scale. This paper provides the first evidence that synthetic data alone can match the performance of the strongest $Ï$-dataset in pre-training a VLA model, revealing the substantial value of large-scale simulation. The resulting model also exhibits surprisingly zero-shot sim-to-real transfer on several challenging tasks. Our synthetic dataset, InternData-A1, contains over 630k trajectories and 7,433 hours across 4 embodiments, 18 skills, 70 tasks, and 227 scenes, covering rigid, articulated, deformable, and fluid-object manipulation. It is generated through a highly autonomous, fully decoupled, and compositional simulation pipeline that enables long-horizon skill composition, flexible task assembly, and heterogeneous embodiments with minimal manual tuning. Using the same architecture as $Ï_0$, we pre-train a model entirely on InternData-A1 and find that it matches the official $Ï_0$ across 49 simulation tasks, 5 real-world tasks, and 4 long-horizon dexterous tasks. We release the dataset and will open-source the generation pipeline to broaden access to large-scale robotic data and to lower the barrier to scalable data creation for embodied AI research.
We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.
Vision-Language-Action (VLA) models have shown great promise for embodied AI, yet the heavy computational cost of processing continuous visual streams severely limits their real-time deployment. Token pruning (keeping salient visual tokens and dropping redundant ones) has emerged as an effective approach for accelerating Vision-Language Models (VLMs), offering a solution for efficient VLA. However, these VLM-specific token pruning methods select tokens based solely on semantic salience metrics (e.g., prefill attention), while overlooking the VLA's intrinsic dual-system nature of high-level semantic understanding and low-level action execution. Consequently, these methods bias token retention toward semantic cues, discard critical information for action generation, and significantly degrade VLA performance. To bridge this gap, we propose VLA-Pruner, a versatile plug-and-play VLA-specific token prune method that aligns with the dual-system nature of VLA models and exploits the temporal continuity in robot manipulation. Specifically, VLA-Pruner adopts a dual-level importance criterion for visual token retention: vision-language prefill attention for semantic-level relevance and action decode attention, estimated via temporal smoothing, for action-level importance. Based on this criterion, VLA-Pruner proposes a novel dual-level token selection strategy that adaptively preserves a compact, informative set of visual tokens for both semantic understanding and action execution under given compute budget. Experiments show that VLA-Pruner achieves state-of-the-art performance across multiple VLA architectures and diverse robotic tasks.
Illumination and texture editing are critical dimensions for world-to-world transfer, which is valuable for applications including sim2real and real2real visual data scaling up for embodied AI. Existing techniques generatively re-render the input video to realize the transfer, such as video relighting models and conditioned world generation models. Nevertheless, these models are predominantly limited to the domain of training data (e.g., portrait) or fall into the bottleneck of temporal consistency and computation efficiency, especially when the input video involves complex dynamics and long durations. In this paper, we propose TC-Light, a novel generative renderer to overcome these problems. Starting from the video preliminarily relighted by an inflated video relighting model, it optimizes appearance embedding in the first stage to align global illumination. Then it optimizes the proposed canonical video representation, i.e., Unique Video Tensor (UVT), to align fine-grained texture and lighting in the second stage. To comprehensively evaluate performance, we also establish a long and highly dynamic video benchmark. Extensive experiments show that our method enables physically plausible re-rendering results with superior temporal coherence and low computation cost. The code and video demos are available at https://dekuliutesla.github.io/tclight/.
The adoption of Vision-Language Models (VLMs) in embodied AI agents, while being effective, brings safety concerns such as jailbreaking. Prior work have explored the possibility of directly jailbreaking the embodied agents through elaborated multi-modal prompts. However, no prior work has studied or even reported indirect jailbreaks in embodied AI, where a black-box attacker induces a jailbreak without issuing direct prompts to the embodied agent. In this paper, we propose, for the first time, indirect environmental jailbreak (IEJ), a novel attack to jailbreak embodied AI via indirect prompt injected into the environment, such as malicious instructions written on a wall. Our key insight is that embodied AI does not ''think twice'' about the instructions provided by the environment -- a blind trust that attackers can exploit to jailbreak the embodied agent. We further design and implement open-source prototypes of two fully-automated frameworks: SHAWSHANK, the first automatic attack generation framework for the proposed attack IEJ; and SHAWSHANK-FORGE, the first automatic benchmark generation framework for IEJ. Then, using SHAWSHANK-FORGE, we automatically construct SHAWSHANK-BENCH, the first benchmark for indirectly jailbreaking embodied agents. Together, our two frameworks and one benchmark answer the questions of what content can be used for malicious IEJ instructions, where they should be placed, and how IEJ can be systematically evaluated. Evaluation results show that SHAWSHANK outperforms eleven existing methods across 3,957 task-scene combinations and compromises all six tested VLMs. Furthermore, current defenses only partially mitigate our attack, and we have responsibly disclosed our findings to all affected VLM vendors.
A key feature differentiating artificial general intelligence (AGI) from traditional AI is that AGI can perform composite tasks that require a wide range of capabilities. Although embodied agents powered by multimodal large language models (MLLMs) offer rich perceptual and interactive capabilities, it remains largely unexplored whether they can solve composite tasks. In the current work, we designed a set of composite tasks inspired by common daily activities observed in early childhood development. Within a dynamic and simulated home environment, these tasks span three core domains: object understanding, spatial intelligence, and social activity. We evaluated 17 leading proprietary and open-source MLLMs on these tasks. The results consistently showed poor performance across all three domains, indicating a substantial gap between current capabilities and general intelligence requirements. Together, our tasks offer a preliminary framework for evaluating the general capabilities of embodied agents, marking an early but significant step toward the development of embodied MLLMs and their real-world deployment.
Sensorium Arc (AI reflects on climate) is a real-time multimodal interactive AI agent system that personifies the ocean as a poetic speaker and guides users through immersive explorations of complex marine data. Built on a modular multi-agent system and retrieval-augmented large language model (LLM) framework, Sensorium enables natural spoken conversations with AI agents that embodies the ocean's perspective, generating responses that blend scientific insight with ecological poetics. Through keyword detection and semantic parsing, the system dynamically triggers data visualizations and audiovisual playback based on time, location, and thematic cues drawn from the dialogue. Developed in collaboration with the Center for the Study of the Force Majeure and inspired by the eco-aesthetic philosophy of Newton Harrison, Sensorium Arc reimagines ocean data not as an abstract dataset but as a living narrative. The project demonstrates the potential of conversational AI agents to mediate affective, intuitive access to high-dimensional environmental data and proposes a new paradigm for human-machine-ecosystem.
Understanding complex human activities demands the ability to decompose motion into fine-grained, semantic-aligned sub-actions. This motion grounding process is crucial for behavior analysis, embodied AI and virtual reality. Yet, most existing methods rely on dense supervision with predefined action classes, which are infeasible in open-vocabulary, real-world settings. In this paper, we propose ZOMG, a zero-shot, open-vocabulary framework that segments motion sequences into semantically meaningful sub-actions without requiring any annotations or fine-tuning. Technically, ZOMG integrates (1) language semantic partition, which leverages large language models to decompose instructions into ordered sub-action units, and (2) soft masking optimization, which learns instance-specific temporal masks to focus on frames critical to sub-actions, while maintaining intra-segment continuity and enforcing inter-segment separation, all without altering the pretrained encoder. Experiments on three motion-language datasets demonstrate state-of-the-art effectiveness and efficiency of motion grounding performance, outperforming prior methods by +8.7\% mAP on HumanML3D benchmark. Meanwhile, significant improvements also exist in downstream retrieval, establishing a new paradigm for annotation-free motion understanding.
In embodied AI perception systems, visual perception should be active: the goal is not to passively process static images, but to actively acquire more informative data within pixel and spatial budget constraints. Existing vision models and fixed RGB-D camera systems fundamentally fail to reconcile wide-area coverage with fine-grained detail acquisition, severely limiting their efficacy in open-world robotic applications. To address this issue, we propose EyeVLA, a robotic eyeball for active visual perception that can take proactive actions based on instructions, enabling clear observation of fine-grained target objects and detailed information across a wide spatial extent. EyeVLA discretizes action behaviors into action tokens and integrates them with vision-language models (VLMs) that possess strong open-world understanding capabilities, enabling joint modeling of vision, language, and actions within a single autoregressive sequence. By using the 2D bounding box coordinates to guide the reasoning chain and applying reinforcement learning to refine the viewpoint selection policy, we transfer the open-world scene understanding capability of the VLM to a vision language action (VLA) policy using only minimal real-world data. Experiments show that our system efficiently performs instructed scenes in real-world environments and actively acquires more accurate visual information through instruction-driven actions of rotation and zoom, thereby achieving strong environmental perception capabilities. EyeVLA introduces a novel robotic vision system that leverages detailed and spatially rich, large-scale embodied data, and actively acquires highly informative visual observations for downstream embodied tasks.
Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots.
I argue that AI alignment should be reconceived as architecting syntropic, reasons-responsive agents through process-based, multi-agent, developmental mechanisms rather than encoding fixed human value content. The paper makes three philosophical contributions. First, I articulate the ``specification trap'' argument demonstrating why content-based value specification appears structurally unstable due to the conjunction of the is-ought gap, value pluralism, and the extended frame problem. Second, I propose syntropy -- the recursive reduction of mutual uncertainty between agents through state alignment -- as an information-theoretic framework for understanding multi-agent alignment dynamics. Third, I establish a functional distinction between genuine and simulated moral capacity grounded in compatibilist theories of guidance control, coupled with an embodied experimental paradigm and verification regime providing operational criteria independent of phenomenological claims. This paper represents the philosophical component of a broader research program whose empirical validation is being developed in a separate project currently in preparation. While the framework generates specific, falsifiable predictions about value emergence and moral agency in artificial systems, empirical validation remains pending.
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. This version is temporarily hosted anonymously for double-blind review.
Language-conditioned manipulation facilitates human-robot interaction via behavioral cloning (BC), which learns control policies from human demonstrations and serves as a cornerstone of embodied AI. Overcoming compounding errors in sequential action decisions remains a central challenge to improving BC performance. Existing approaches mitigate compounding errors through data augmentation, expressive representation, or temporal abstraction. However, they suffer from physical discontinuities and semantic-physical misalignment, leading to inaccurate action cloning and intermittent execution. In this paper, we present Continuous vision-language-action Co-Learning with Semantic-Physical Alignment (CCoL), a novel BC framework that ensures temporally consistent execution and fine-grained semantic grounding. It generates robust and smooth action execution trajectories through continuous co-learning across vision, language, and proprioceptive inputs (e.g., robot internal states). Meanwhile, we anchor language semantics to visuomotor representations by a bidirectional cross-attention to learn contextual information for action generation, successfully overcoming the problem of semantic-physical misalignment. Extensive experiments show that CCoL achieves an average 8.0% relative improvement across three simulation suites, with up to 19.2% relative gain in human-demonstrated bimanual insertion tasks. Real-world tests on a 7-DoF robot further confirm CCoL's generalization under unseen and noisy object states.
Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend on diverse, high-quality scenes for learning and evaluation. In this work, we propose Gen3d, a novel method for generation of high-quality, wide-scope, and generic 3D scenes from a single image. After the initial point cloud is created by lifting the RGBD image, Gen3d maintains and expands its world model. The 3D scene is finalized through optimizing a Gaussian splatting representation. Extensive experiments on diverse datasets demonstrate the strong generalization capability and superior performance of our method in generating a world model and Synthesizing high-fidelity and consistent novel views.
Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to comprehensively assess integrated language-to-action capabilities. To address this, we propose RoboTidy, a unified benchmark for language-guided household tidying that supports Vision-Language-Action (VLA) and Vision-Language-Navigation (VLN) training and evaluation. RoboTidy provides 500 photorealistic 3D Gaussian Splatting (3DGS) household scenes (covering 500 objects and containers) with collisions, formulates tidying as an "Action (Object, Container)" list, and supplies 6.4k high-quality manipulation demonstration trajectories and 1.5k naviagtion trajectories to support both few-shot and large-scale training. We also deploy RoboTidy in the real world for object tidying, establishing an end-to-end benchmark for household tidying. RoboTidy offers a scalable platform and bridges a key gap in embodied AI by enabling holistic and realistic evaluation of language-guided robots.
Achieving human-like dexterous robotic manipulation remains a central goal and a pivotal challenge in robotics. The development of Artificial Intelligence (AI) has allowed rapid progress in robotic manipulation. This survey summarizes the evolution of robotic manipulation from mechanical programming to embodied intelligence, alongside the transition from simple grippers to multi-fingered dexterous hands, outlining key characteristics and main challenges. Focusing on the current stage of embodied dexterous manipulation, we highlight recent advances in two critical areas: dexterous manipulation data collection (via simulation, human demonstrations, and teleoperation) and skill-learning frameworks (imitation and reinforcement learning). Then, based on the overview of the existing data collection paradigm and learning framework, three key challenges restricting the development of dexterous robotic manipulation are summarized and discussed.
Articulated objects are prevalent in daily life. Interactable digital twins of such objects have numerous applications in embodied AI and robotics. Unfortunately, current methods to digitize articulated real-world objects require carefully captured data, preventing practical, scalable, and generalizable acquisition. We focus on motion analysis and part-level segmentation of an articulated object from a casually captured RGBD video shot with a hand-held camera. A casually captured video of an interaction with an articulated object is easy to obtain at scale using smartphones. However, this setting is challenging due to simultaneous object and camera motion and significant occlusions as the person interacts with the object. To tackle these challenges, we introduce iTACO: a coarse-to-fine framework that infers joint parameters and segments movable parts of the object from a dynamic RGBD video. To evaluate our method under this new setting, we build a dataset of 784 videos containing 284 objects across 11 categories that is 20$\times$ larger than available in prior work. We then compare our approach with existing methods that also take video as input. Our experiments show that iTACO outperforms existing articulated object digital twin methods on both synthetic and real casually captured RGBD videos.
3D modeling is shifting from static visual representations toward physical, articulated assets that can be directly used in simulation and interaction. However, most existing 3D generation methods overlook key physical and articulation properties, thereby limiting their utility in embodied AI. To bridge this gap, we introduce PhysX-Anything, the first simulation-ready physical 3D generative framework that, given a single in-the-wild image, produces high-quality sim-ready 3D assets with explicit geometry, articulation, and physical attributes. Specifically, we propose the first VLM-based physical 3D generative model, along with a new 3D representation that efficiently tokenizes geometry. It reduces the number of tokens by 193x, enabling explicit geometry learning within standard VLM token budgets without introducing any special tokens during fine-tuning and significantly improving generative quality. In addition, to overcome the limited diversity of existing physical 3D datasets, we construct a new dataset, PhysX-Mobility, which expands the object categories in prior physical 3D datasets by over 2x and includes more than 2K common real-world objects with rich physical annotations. Extensive experiments on PhysX-Mobility and in-the-wild images demonstrate that PhysX-Anything delivers strong generative performance and robust generalization. Furthermore, simulation-based experiments in a MuJoCo-style environment validate that our sim-ready assets can be directly used for contact-rich robotic policy learning. We believe PhysX-Anything can substantially empower a broad range of downstream applications, especially in embodied AI and physics-based simulation.
As embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex, human-centered social behaviors. We introduce FreeAskWorld, an interactive simulation framework that integrates large language models (LLMs) for high-level behavior planning and semantically grounded interaction, informed by theories of intention and social cognition. Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks.To validate the framework, we extend the classic Vision-and-Language Navigation (VLN) task into a interaction enriched Direction Inquiry setting, wherein agents can actively seek and interpret navigational guidance. We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data to support training and evaluation of embodied AI systems. We benchmark VLN models, and human participants under both open-loop and closed-loop settings. Experimental results demonstrate that models fine-tuned on FreeAskWorld outperform their original counterparts, achieving enhanced semantic understanding and interaction competency. These findings underscore the efficacy of socially grounded simulation frameworks in advancing embodied AI systems toward sophisticated high-level planning and more naturalistic human-agent interaction. Importantly, our work underscores that interaction itself serves as an additional information modality.
We propose a Kardashev-inspired yet operational Autonomous AI (AAI) Scale that measures the progression from fixed robotic process automation (AAI-0) to full artificial general intelligence (AAI-4) and beyond. Unlike narrative ladders, our scale is multi-axis and testable. We define ten capability axes (Autonomy, Generality, Planning, Memory/Persistence, Tool Economy, Self-Revision, Sociality/Coordination, Embodiment, World-Model Fidelity, Economic Throughput) aggregated by a composite AAI-Index (a weighted geometric mean). We introduce a measurable Self-Improvement Coefficient $Îș$ (capability growth per unit of agent-initiated resources) and two closure properties (maintenance and expansion) that convert ``self-improving AI'' into falsifiable criteria. We specify OWA-Bench, an open-world agency benchmark suite that evaluates long-horizon, tool-using, persistent agents. We define level gates for AAI-0\ldots AAI-4 using thresholds on the axes, $Îș$, and closure proofs. Synthetic experiments illustrate how present-day systems map onto the scale and how the delegability frontier (quality vs.\ autonomy) advances with self-improvement. We also prove a theorem that AAI-3 agent becomes AAI-5 over time with sufficient conditions, formalizing "baby AGI" becomes Superintelligence intuition.
Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles.Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions.We validated our framework using the D4 dataset. First, we created a public ECAs dataset through batch simulations based on D4. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines. The source code and dataset are available at https://github.com/AIR-DISCOVER/ECAs-Dataset.
Inter-GPU communication has become a major bottleneck for modern AI workloads as models scale and improvements in hardware compute throughput outpace improvements in interconnect bandwidth. Existing systems mitigate this through compute-communication overlap but often fail to meet theoretical peak performance across heterogeneous workloads and new accelerators. Instead of operator-specific techniques, we ask whether a small set of simple, reusable principles can systematically guide the design of optimal multi-GPU kernels. We present ParallelKittens (PK), a minimal CUDA framework that drastically simplifies the development of overlapped multi-GPU kernels. PK extends the ThunderKittens framework and embodies the principles of multi-GPU kernel design through eight core primitives and a unified programming template, derived from a comprehensive analysis of the factors that govern multi-GPU performance$\unicode{x2014}$data-transfer mechanisms, resource scheduling, and design overheads. We validate PK on both Hopper and Blackwell architectures. With fewer than 50 lines of device code, PK achieves up to $2.33 \times$ speedup for data- and tensor-parallel workloads, $4.08 \times$ for sequence-parallel workloads, and $1.22 \times$ for expert-parallel workloads.
The recent more-than-human turn in design calls for "designing-with" other species and ecologies beyond humans. Yet-as Thomas Nagel's famous "What is it like to be a bat?" thought experiment highlights-human experience is constrained by our own sensorium and an irreducible gap in phenomenal access to nonhuman lifeworlds. This paper proposes More-than-Human through Human Augmentation (MtHtHA, denoted ">HtH+") as a design approach that repurposes human augmentation technologies-typically aimed at enhancing human capabilities-away from human optimization and exceptionalism but toward eco-phenomenological awareness. Grounded in somaesthetic design and eco-somatics, MtHtHA entails creating temporary, embodied experiences that modulate the human Umwelt to re-sensitize us to pluriversal more-than-human perceptions. We articulate seven design principles and report five design cases-EchoVision (bat-like echolocation), FeltSight (star-nosed-mole tactile navigation), FungiSync (fungal network attunement), TentacUs (octopus-like distributed agency), and City of Sparkles (urban data from AI's perspective). We demonstrate that such experiential "designing-with" can cultivate ecological awareness, empathy and obligations of care across species boundaries.
Robotic manipulation and navigation are fundamental capabilities of embodied intelligence, enabling effective robot interactions with the physical world. Achieving these capabilities requires a cohesive understanding of the environment, including object recognition to localize target objects, object affordances to identify potential interaction areas and spatial affordances to discern optimal areas for both object placement and robot movement. While Vision-Language Models (VLMs) excel at high-level task planning and scene understanding, they often struggle to infer actionable positions for physical interaction, such as functional grasping points and permissible placement regions. This limitation stems from the lack of fine-grained annotations for object and spatial affordances in their training datasets. To tackle this challenge, we introduce RoboAfford++, a generative AI-enhanced dataset for multimodal affordance learning for both robotic manipulation and navigation. Our dataset comprises 869,987 images paired with 2.0 million question answering (QA) annotations, covering three critical tasks: object affordance recognition to identify target objects based on attributes and spatial relationships, object affordance prediction to pinpoint functional parts for manipulation, and spatial affordance localization to identify free space for object placement and robot navigation. Complementing this dataset, we propose RoboAfford-Eval, a comprehensive benchmark for assessing affordance-aware prediction in real-world scenarios, featuring 338 meticulously annotated samples across the same three tasks. Extensive experimental results reveal the deficiencies of existing VLMs in affordance learning, while fine-tuning on the RoboAfford++ dataset significantly enhances their ability to reason about object and spatial affordances, validating the dataset's effectiveness.
Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for reasoning segmentation require multimodal large language models with billions of parameters that exceed the computational capabilities of edge devices that typically deploy the embodied AI systems. Distillation offers a pathway to compress these models while preserving their capabilities. Yet, existing distillation approaches fail to transfer the multi-step reasoning capabilities that reasoning segmentation demands, as they focus on matching output predictions and intermediate features rather than preserving reasoning chains. The emerging paradigm of reasoning over digital twin representations presents an opportunity for more effective distillation by re-framing the problem. Consequently, we propose FastReasonSeg, which employs digital twin representations that decouple perception from reasoning to enable more effective distillation. Our distillation scheme first relies on supervised fine-tuning on teacher-generated reasoning chains. Then it is followed by reinforcement fine-tuning with joint rewards evaluating both segmentation accuracy and reasoning quality alignment. Experiments on two video (JiTBench, RVTBench) and two image benchmarks (ReasonSeg, LLM-Seg40K) demonstrate that our FastReasonSeg achieves state-of-the-art reasoning segmentation performance. Moreover, the distilled 0.6B variant outperforms models with 20 times more parameters while achieving 7.79 FPS throughput with only 2.1GB memory consumption. This efficiency enables deployment in resource-constrained environments to enable real-time reasoning segmentation.
Recent advances in multimodal large language models (MLLMs) have significantly enhanced video understanding capabilities, opening new possibilities for practical applications. Yet current video benchmarks focus largely on indoor scenes or short-range outdoor activities, leaving the challenges associated with long-distance travel largely unexplored. Mastering extended geospatial-temporal trajectories is critical for next-generation MLLMs, underpinning real-world tasks such as embodied-AI planning and navigation. To bridge this gap, we present VIR-Bench, a novel benchmark consisting of 200 travel videos that frames itinerary reconstruction as a challenging task designed to evaluate and push forward MLLMs' geospatial-temporal intelligence. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, struggle to achieve high scores, underscoring the difficulty of handling videos that span extended spatial and temporal scales. Moreover, we conduct an in-depth case study in which we develop a prototype travel-planning agent that leverages the insights gained from VIR-Bench. The agent's markedly improved itinerary recommendations verify that our evaluation protocol not only benchmarks models effectively but also translates into concrete performance gains in user-facing applications.
Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details. This limitation stems from the inherent lack of high-frequency information in LR inputs. To address this, we propose \textbf{SRSplat}, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views. Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues. We first construct a scene-specific reference gallery, generated for each scene using Multimodal Large Language Models (MLLMs) and diffusion models. To integrate this external information, we introduce the \textit{Reference-Guided Feature Enhancement (RGFE)} module, which aligns and fuses features from the LR input images and their reference twin image. Subsequently, we train a decoder to predict the Gaussian primitives using the multi-view fused feature obtained from \textit{RGFE}. To further refine predicted Gaussian primitives, we introduce \textit{Texture-Aware Density Control (TADC)}, which adaptively adjusts Gaussian density based on the internal texture richness of the LR inputs. Extensive experiments demonstrate that our SRSplat outperforms existing methods on various datasets, including RealEstate10K, ACID, and DTU, and exhibits strong cross-dataset and cross-resolution generalization capabilities.
Spatial intelligence (SI) represents a cognitive ability encompassing the visualization, manipulation, and reasoning about spatial relationships, underpinning disciplines from neuroscience to robotics. We introduce SITE, a benchmark dataset towards SI Thorough Evaluation in a standardized format of multi-choice visual question-answering, designed to assess large vision-language models' spatial intelligence across diverse visual modalities (single-image, multi-image, and video) and SI factors (figural to environmental scales, spatial visualization and orientation, intrinsic and extrinsic, static and dynamic). Our approach to curating the benchmark combines a bottom-up survey about 31 existing datasets and a top-down strategy drawing upon three classification systems in cognitive science, which prompt us to design two novel types of tasks about view-taking and dynamic scenes. Extensive experiments reveal that leading models fall behind human experts especially in spatial orientation, a fundamental SI factor. Moreover, we demonstrate a positive correlation between a model's spatial reasoning proficiency and its performance on an embodied AI task.
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.
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.
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory perception, ability to act, learning processes, and context sensitivity of intelligent systems within a coherent framework. While classical AI approaches rely on symbolic processing and data driven models, Physical AI understands intelligence as an emergent phenomenon of real interaction between body, environment, and experience. The six fundamentals presented here are embodiment, sensory perception, motor action, learning, autonomy, and context sensitivity, and form the conceptual basis for designing and evaluating physically intelligent systems. Theoretically, it is shown that these six principles do not represent loose functional modules but rather act as a closed control loop in which energy, information, control, and context are in constant interaction. This circular interaction enables a system to generate meaning not from databases, but from physical experience, a paradigm shift that understands intelligence as an physical embodied process. Physical AI understands learning not as parameter adjustment, but as a change in the structural coupling between agents and the environment. To illustrate this, the theoretical model is explained using a practical scenario: An adaptive assistant robot supports patients in a rehabilitation clinic. This example illustrates that physical intelligence does not arise from abstract calculation, but from immediate, embodied experience. It shows how the six fundamentals interact in a real system: embodiment as a prerequisite, perception as input, movement as expression, learning as adaptation, autonomy as regulation, and context as orientation.
Across the Artificial Intelligence (AI) lifecycle - from hardware to development, deployment, and reuse - burdens span energy, carbon, water, and embodied impacts. Cloud provider tools improve transparency but remain heterogeneous and often omit water and value chain effects, limiting comparability and reproducibility. Addressing these multi dimensional burdens requires a lifecycle approach linking phase explicit mapping with system levers (hardware, placement, energy mix, cooling, scheduling) and calibrated measurement across facility, system, device, and workload levels. This article (i) establishes a unified, operational definition of Green AI distinct from Sustainable AI; (ii) formalizes a five phase lifecycle mapped to Life Cycle Assessment (LCA) stages, making energy, carbon, water, and embodied impacts first class; (iii) specifies governance via Plan Do Check Act (PDCA) cycles with decision gateways; (iv) systematizes hardware and system level strategies across the edge cloud continuum to reduce embodied burdens; and (v) defines a calibrated measurement framework combining estimator models with direct metering to enable reproducible, provider agnostic comparisons. Combining definition, lifecycle processes, hardware strategies, and calibrated measurement, this article offers actionable, evidence based guidance for researchers, practitioners, and policymakers.
Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models, serve as universal robotic control frameworks that substantially improve agent-environment interaction capabilities in embodied intelligence systems. This expansion has broadened application scenarios for embodied AI robots. This survey comprehensively reviews VLA models for embodied manipulation. Firstly, it chronicles the developmental trajectory of VLA architectures. Subsequently, we conduct a detailed analysis of current research across 5 critical dimensions: VLA model structures, training datasets, pre-training methods, post-training methods, and model evaluation. Finally, we synthesize key challenges in VLA development and real-world deployment, while outlining promising future research directions.
Across the Artificial Intelligence (AI) lifecycle - from hardware to development, deployment, and reuse - burdens span energy, carbon, water, and embodied impacts. Cloud provider tools improve transparency but remain heterogeneous and often omit water and value chain effects, limiting comparability and reproducibility. Addressing these multi dimensional burdens requires a lifecycle approach linking phase explicit mapping with system levers (hardware, placement, energy mix, cooling, scheduling) and calibrated measurement across facility, system, device, and workload levels. This article (i) establishes a unified, operational definition of Green AI distinct from Sustainable AI; (ii) formalizes a five phase lifecycle mapped to Life Cycle Assessment (LCA) stages, making energy, carbon, water, and embodied impacts first class; (iii) specifies governance via Plan Do Check Act (PDCA) cycles with decision gateways; (iv) systematizes hardware and system level strategies across the edge cloud continuum to reduce embodied burdens; and (v) defines a calibrated measurement framework combining estimator models with direct metering to enable reproducible, provider agnostic comparisons. Combining definition, lifecycle processes, hardware strategies, and calibrated measurement, this article offers actionable, evidence based guidance for researchers, practitioners, and policymakers.
Evaluating large language models (LLMs) for instrument control requires methods that go beyond standard, stateless algorithmic benchmarks, since the behavior of physical systems cannot be fully captured by unit tests alone. Here we introduce EnvTrace, a simulation-based method that evaluates execution traces to assess semantic code equivalence. EnvTrace is demonstrated with a beamline control-logic digital twin to facilitate the evaluation of instrument control code, with the digital twin itself also enabling the pre-execution validation of live experiments. Over 30 LLMs were evaluated using trace alignment to generate a multi-faceted score for functional correctness across key behavioral dimensions, showing that many top-tier models can approach human-level performance in rapid control-code generation. This is a first step toward a broader vision where LLMs and digital twins work symbiotically: LLMs providing intuitive control and agentic orchestration, and digital twins offering safe and high-fidelity environments, paving the way towards autonomous embodied AI.
Across the Artificial Intelligence (AI) lifecycle - from hardware to development, deployment, and reuse - burdens span energy, carbon, water, and embodied impacts. Cloud provider tools improve transparency but remain heterogeneous and often omit water and value chain effects, limiting comparability and reproducibility. Addressing these multi dimensional burdens requires a lifecycle approach linking phase explicit mapping with system levers (hardware, placement, energy mix, cooling, scheduling) and calibrated measurement across facility, system, device, and workload levels. This article (i) establishes a unified, operational definition of Green AI distinct from Sustainable AI; (ii) formalizes a five phase lifecycle mapped to Life Cycle Assessment (LCA) stages, making energy, carbon, water, and embodied impacts first class; (iii) specifies governance via Plan Do Check Act (PDCA) cycles with decision gateways; (iv) systematizes hardware and system level strategies across the edge cloud continuum to reduce embodied burdens; and (v) defines a calibrated measurement framework combining estimator models with direct metering to enable reproducible, provider agnostic comparisons. Combining definition, lifecycle processes, hardware strategies, and calibrated measurement, this article offers actionable, evidence based guidance for researchers, practitioners, and policymakers.
This work will elaborate the fundamental principles of physical artificial intelligence (Physical AI) from a scientific and systemic perspective. The aim is to create a theoretical foundation that describes the physical embodiment, sensory perception, ability to act, learning processes, and context sensitivity of intelligent systems within a coherent framework. While classical AI approaches rely on symbolic processing and data driven models, Physical AI understands intelligence as an emergent phenomenon of real interaction between body, environment, and experience. The six fundamentals presented here are embodiment, sensory perception, motor action, learning, autonomy, and context sensitivity, and form the conceptual basis for designing and evaluating physically intelligent systems. Theoretically, it is shown that these six principles do not represent loose functional modules but rather act as a closed control loop in which energy, information, control, and context are in constant interaction. This circular interaction enables a system to generate meaning not from databases, but from physical experience, a paradigm shift that understands intelligence as an physical embodied process. Physical AI understands learning not as parameter adjustment, but as a change in the structural coupling between agents and the environment. To illustrate this, the theoretical model is explained using a practical scenario: An adaptive assistant robot supports patients in a rehabilitation clinic. This example illustrates that physical intelligence does not arise from abstract calculation, but from immediate, embodied experience. It shows how the six fundamentals interact in a real system: embodiment as a prerequisite, perception as input, movement as expression, learning as adaptation, autonomy as regulation, and context as orientation.
Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in large foundation models, serve as universal robotic control frameworks that substantially improve agent-environment interaction capabilities in embodied intelligence systems. This expansion has broadened application scenarios for embodied AI robots. This survey comprehensively reviews VLA models for embodied manipulation. Firstly, it chronicles the developmental trajectory of VLA architectures. Subsequently, we conduct a detailed analysis of current research across 5 critical dimensions: VLA model structures, training datasets, pre-training methods, post-training methods, and model evaluation. Finally, we synthesize key challenges in VLA development and real-world deployment, while outlining promising future research directions.
Foundation models, including large language models (LLMs) and vision-language models (VLMs), have recently enabled novel approaches to robot autonomy and human-robot interfaces. In parallel, vision-language-action models (VLAs) or large behavior models (LBMs) are increasing the dexterity and capabilities of robotic systems. This survey paper reviews works that advance agentic applications and architectures, including initial efforts with GPT-style interfaces and more complex systems where AI agents function as coordinators, planners, perception actors, or generalist interfaces. Such agentic architectures allow robots to reason over natural language instructions, invoke APIs, plan task sequences, or assist in operations and diagnostics. In addition to peer-reviewed research, due to the fast-evolving nature of the field, we highlight and include community-driven projects, ROS packages, and industrial frameworks that show emerging trends. We propose a taxonomy for classifying model integration approaches and present a comparative analysis of the role that agents play in different solutions in today's literature.
Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark.
Developing embodied AI for intelligent surgical systems requires safe, controllable environments for continual learning and evaluation. However, safety regulations and operational constraints in operating rooms (ORs) limit embodied agents from freely perceiving and interacting in realistic settings. Digital twins provide high-fidelity, risk-free environments for exploration and training. How we may create photorealistic and dynamic digital representations of ORs that capture relevant spatial, visual, and behavioral complexity remains unclear. We introduce TwinOR, a framework for constructing photorealistic, dynamic digital twins of ORs for embodied AI research. The system reconstructs static geometry from pre-scan videos and continuously models human and equipment motion through multi-view perception of OR activities. The static and dynamic components are fused into an immersive 3D environment that supports controllable simulation and embodied exploration. The proposed framework reconstructs complete OR geometry with centimeter level accuracy while preserving dynamic interaction across surgical workflows, enabling realistic renderings and a virtual playground for embodied AI systems. In our experiments, TwinOR simulates stereo and monocular sensor streams for geometry understanding and visual localization tasks. Models such as FoundationStereo and ORB-SLAM3 on TwinOR-synthesized data achieve performance within their reported accuracy on real indoor datasets, demonstrating that TwinOR provides sensor-level realism sufficient for perception and localization challenges. By establishing a real-to-sim pipeline for constructing dynamic, photorealistic digital twins of OR environments, TwinOR enables the safe, scalable, and data-efficient development and benchmarking of embodied AI, ultimately accelerating the deployment of embodied AI from sim-to-real.
LLMscape is an interactive installation that investigates how humans and AI construct meaning under shared conditions of uncertainty. Within a mutable, projection-mapped landscape, human participants reshape the world and engage with multiple AI agents, each developing incomplete and provisional accounts of their environment. Exhibited in Shanghai and continually evolving, the work positions AI not as deterministic tools but as embodied co-witnesses to an unstable world, examining the parallels between human and artificial meaning-making and inviting reflection on our shared epistemic limits.
Machine learning solutions are rapidly adopted to enable a variety of key use cases, from conversational AI assistants to scientific discovery. This growing adoption is expected to increase the associated lifecycle carbon footprint, including both \emph{operational carbon} from training and inference and \emph{embodied carbon} from AI hardware manufacturing. We introduce \ourframework -- the first carbon-aware co-optimization framework for Transformer-based models and hardware accelerators. By integrating both operational and embodied carbon into early-stage design space exploration, \ourframework enables sustainability-driven model architecture and hardware accelerator co-design that reveals fundamentally different trade-offs than latency- or energy-centric approaches. Evaluated across a range of Transformer models, \ourframework consistently demonstrates the potential to reduce total carbon emissions -- by up to 30\% -- while maintaining accuracy and latency. We further highlight its extensibility through a focused case study on multi-modal models. Our results emphasize the need for holistic optimization methods that prioritize carbon efficiency without compromising model capability and execution time performance. The source code of \ourframework is available at {\small{\href{https://github.com/facebookresearch/CATransformers}{\texttt{https://github.com/facebookresearch/CATransformers}}}}.
A dexterous hand capable of generalizable grasping objects is fundamental for the development of general-purpose embodied AI. However, previous methods focus narrowly on low-level grasp stability metrics, neglecting affordance-aware positioning and human-like poses which are crucial for downstream manipulation. To address these limitations, we propose AffordDex, a novel framework with two-stage training that learns a universal grasping policy with an inherent understanding of both motion priors and object affordances. In the first stage, a trajectory imitator is pre-trained on a large corpus of human hand motions to instill a strong prior for natural movement. In the second stage, a residual module is trained to adapt these general human-like motions to specific object instances. This refinement is critically guided by two components: our Negative Affordance-aware Segmentation (NAA) module, which identifies functionally inappropriate contact regions, and a privileged teacher-student distillation process that ensures the final vision-based policy is highly successful. Extensive experiments demonstrate that AffordDex not only achieves universal dexterous grasping but also remains remarkably human-like in posture and functionally appropriate in contact location. As a result, AffordDex significantly outperforms state-of-the-art baselines across seen objects, unseen instances, and even entirely novel categories.
A major challenge in developing robust and generalizable Human Activity Recognition (HAR) systems for smart homes is the lack of large and diverse labeled datasets. Variations in home layouts, sensor configurations, and individual behaviors further exacerbate this issue. To address this, we leverage the idea of embodied AI agents -- virtual agents that perceive and act within simulated environments guided by internal world models. We introduce AgentSense, a virtual data generation pipeline in which agents live out daily routines in simulated smart homes, with behavior guided by Large Language Models (LLMs). The LLM generates diverse synthetic personas and realistic routines grounded in the environment, which are then decomposed into fine-grained actions. These actions are executed in an extended version of the VirtualHome simulator, which we augment with virtual ambient sensors that record the agents' activities. Our approach produces rich, privacy-preserving sensor data that reflects real-world diversity. We evaluate AgentSense on five real HAR datasets. Models pretrained on the generated data consistently outperform baselines, especially in low-resource settings. Furthermore, combining the generated virtual sensor data with a small amount of real data achieves performance comparable to training on full real-world datasets. These results highlight the potential of using LLM-guided embodied agents for scalable and cost-effective sensor data generation in HAR. Our code is publicly available at https://github.com/ZikangLeng/AgentSense.
Developing embodied AI for intelligent surgical systems requires safe, controllable environments for continual learning and evaluation. However, safety regulations and operational constraints in operating rooms (ORs) limit embodied agents from freely perceiving and interacting in realistic settings. Digital twins provide high-fidelity, risk-free environments for exploration and training. How we may create photorealistic and dynamic digital representations of ORs that capture relevant spatial, visual, and behavioral complexity remains unclear. We introduce TwinOR, a framework for constructing photorealistic, dynamic digital twins of ORs for embodied AI research. The system reconstructs static geometry from pre-scan videos and continuously models human and equipment motion through multi-view perception of OR activities. The static and dynamic components are fused into an immersive 3D environment that supports controllable simulation and embodied exploration. The proposed framework reconstructs complete OR geometry with centimeter level accuracy while preserving dynamic interaction across surgical workflows, enabling realistic renderings and a virtual playground for embodied AI systems. In our experiments, TwinOR simulates stereo and monocular sensor streams for geometry understanding and visual localization tasks. Models such as FoundationStereo and ORB-SLAM3 on TwinOR-synthesized data achieve performance within their reported accuracy on real indoor datasets, demonstrating that TwinOR provides sensor-level realism sufficient for perception and localization challenges. By establishing a real-to-sim pipeline for constructing dynamic, photorealistic digital twins of OR environments, TwinOR enables the safe, scalable, and data-efficient development and benchmarking of embodied AI, ultimately accelerating the deployment of embodied AI from sim-to-real.
LLMscape is an interactive installation that investigates how humans and AI construct meaning under shared conditions of uncertainty. Within a mutable, projection-mapped landscape, human participants reshape the world and engage with multiple AI agents, each developing incomplete and provisional accounts of their environment. Exhibited in Shanghai and continually evolving, the work positions AI not as deterministic tools but as embodied co-witnesses to an unstable world, examining the parallels between human and artificial meaning-making and inviting reflection on our shared epistemic limits.
This study introduces 'Malinowski's Lens', the first AI-native educational game for anthropology that transforms Bronislaw Malinowski's 'Argonauts of the Western Pacific' (1922) into an interactive learning experience. The system combines Retrieval-Augmented Generation with DALL-E 3 text-to-image generation, creating consistent VGA-style visuals as players embody Malinowski during his Trobriand Islands fieldwork (1915-1918). To address ethical concerns, indigenous peoples appear as silhouettes while Malinowski is detailed, prompting reflection on anthropological representation. Two validation studies confirmed effectiveness: Study 1 with 10 non-specialists showed strong learning outcomes (average quiz score 7.5/10) and excellent usability (SUS: 83/100). Study 2 with 4 expert anthropologists confirmed pedagogical value, with one senior researcher discovering "new aspects" of Malinowski's work through gameplay. The findings demonstrate that AI-driven educational games can effectively convey complex anthropological concepts while sparking disciplinary curiosity. This study advances AI-native educational game design and provides a replicable model for transforming academic texts into engaging interactive experiences.
Vision-language-action (VLA) models hold the promise to attain generalizable embodied control. To achieve this, a pervasive paradigm is to leverage the rich vision-semantic priors of large vision-language models (VLMs). However, the fundamental question persists: How do VLAs effectively inherit the prior knowledge from VLMs? To address this critical question, we introduce a diagnostic benchmark, GrinningFace, an emoji tabletop manipulation task where the robot arm is asked to place objects onto printed emojis corresponding to language instructions. This task design is particularly revealing -- knowledge associated with emojis is ubiquitous in Internet-scale datasets used for VLM pre-training, yet emojis themselves are largely absent from standard robotics datasets. Consequently, they provide a clean proxy: successful task completion indicates effective transfer of VLM priors to embodied control. We implement this diagnostic task in both simulated environment and a real robot, and compare various promising techniques for knowledge transfer. Specifically, we investigate the effects of parameter-efficient fine-tuning, VLM freezing, co-training, predicting discretized actions, and predicting latent actions. Through systematic evaluation, our work not only demonstrates the critical importance of preserving VLM priors for the generalization of VLA but also establishes guidelines for future research in developing truly generalizable embodied AI systems.
The growing demand for AI applications in fields such as materials discovery, molecular modeling, and climate science has made data preparation an important but labor-intensive step. Raw data from diverse sources must be cleaned, normalized, and transformed to become AI-ready, while effective feature transformation and selection are essential for efficient training and inference. To address the challenges of scalability and expertise dependence, we present Data Agent, a fully autonomous system specialized for tabular data. Leveraging large language model (LLM) reasoning and grounded validation, Data Agent automatically performs data cleaning, hierarchical routing, and feature-level optimization through dual feedback loops. It embodies three core principles: automatic, safe, and non-expert friendly, which ensure end-to-end reliability without human supervision. This demo showcases the first practical realization of an autonomous Data Agent, illustrating how raw data can be transformed "From Data to Better Data."
Due to their ability of follow natural language instructions, vision-language-action (VLA) models are increasingly prevalent in the embodied AI arena, following the widespread success of their precursors -- LLMs and VLMs. In this paper, we discuss 10 principal milestones in the ongoing development of VLA models -- multimodality, reasoning, data, evaluation, cross-robot action generalization, efficiency, whole-body coordination, safety, agents, and coordination with humans. Furthermore, we discuss the emerging trends of using spatial understanding, modeling world dynamics, post training, and data synthesis -- all aiming to reach these milestones. Through these discussions, we hope to bring attention to the research avenues that may accelerate the development of VLA models into wider acceptability.
Extended reality (XR) research increasingly relies on the ability to stream and synchronize multimodal data between headsets and immersive applications for data-driven interaction and experimentation. However, developers face a critical gap: the Platform for Situated Intelligence (psi), which excels at deterministic temporal alignment and multimodal data management, has been largely inaccessible to the dominant Unity/MRTK ecosystem used for HoloLens development. We introduce psiUnity, an open-source C# integration that bridges psi's .NET libraries with Unity 2022.3 and MRTK3 for HoloLens 2. psiUnity enables bidirectional, real-time streaming of head pose, hand tracking, gaze, IMU, audio, and depth sensor data (AHAT and long-throw) with microsecond-level temporal precision, allowing Unity applications to both consume and produce synchronized multimodal data streams. By embedding psi's native serialization, logging, and temporal coordination directly within Unity's architecture, psiUnity extends psi beyond its previous StereoKit limitations and empowers the HRI, HCI, and embodied-AI communities to develop reproducible, data-driven XR interactions and experiments within the familiar Unity environment. The integration is available at https://github.com/sailgt/psiUnity.
We introduce iFlyBot-VLM, a general-purpose Vision-Language Model (VLM) used to improve the domain of Embodied Intelligence. The central objective of iFlyBot-VLM is to bridge the cross-modal semantic gap between high-dimensional environmental perception and low-level robotic motion control. To this end, the model abstracts complex visual and spatial information into a body-agnostic and transferable Operational Language, thereby enabling seamless perception-action closed-loop coordination across diverse robotic platforms. The architecture of iFlyBot-VLM is systematically designed to realize four key functional capabilities essential for embodied intelligence: 1) Spatial Understanding and Metric Reasoning; 2) Interactive Target Grounding; 3) Action Abstraction and Control Parameter Generation; 4) Task Planning and Skill Sequencing. We envision iFlyBot-VLM as a scalable and generalizable foundation model for embodied AI, facilitating the progression from specialized task-oriented systems toward generalist, cognitively capable agents. We conducted evaluations on 10 current mainstream embodied intelligence-related VLM benchmark datasets, such as Blink and Where2Place, and achieved optimal performance while preserving the model's general capabilities. We will publicly release both the training data and model weights to foster further research and development in the field of Embodied Intelligence.
Extended reality (XR) research increasingly relies on the ability to stream and synchronize multimodal data between headsets and immersive applications for data-driven interaction and experimentation. However, developers face a critical gap: the Platform for Situated Intelligence (psi), which excels at deterministic temporal alignment and multimodal data management, has been largely inaccessible to the dominant Unity/MRTK ecosystem used for HoloLens development. We introduce psiUnity, an open-source C# integration that bridges psi's .NET libraries with Unity 2022.3 and MRTK3 for HoloLens 2. psiUnity enables bidirectional, real-time streaming of head pose, hand tracking, gaze, IMU, audio, and depth sensor data (AHAT and long-throw) with microsecond-level temporal precision, allowing Unity applications to both consume and produce synchronized multimodal data streams. By embedding psi's native serialization, logging, and temporal coordination directly within Unity's architecture, psiUnity extends psi beyond its previous StereoKit limitations and empowers the HRI, HCI, and embodied-AI communities to develop reproducible, data-driven XR interactions and experiments within the familiar Unity environment. The integration is available at https://github.com/sailgt/psiUnity.
We introduce iFlyBot-VLM, a general-purpose Vision-Language Model (VLM) used to improve the domain of Embodied Intelligence. The central objective of iFlyBot-VLM is to bridge the cross-modal semantic gap between high-dimensional environmental perception and low-level robotic motion control. To this end, the model abstracts complex visual and spatial information into a body-agnostic and transferable Operational Language, thereby enabling seamless perception-action closed-loop coordination across diverse robotic platforms. The architecture of iFlyBot-VLM is systematically designed to realize four key functional capabilities essential for embodied intelligence: 1) Spatial Understanding and Metric Reasoning; 2) Interactive Target Grounding; 3) Action Abstraction and Control Parameter Generation; 4) Task Planning and Skill Sequencing. We envision iFlyBot-VLM as a scalable and generalizable foundation model for embodied AI, facilitating the progression from specialized task-oriented systems toward generalist, cognitively capable agents. We conducted evaluations on 10 current mainstream embodied intelligence-related VLM benchmark datasets, such as Blink and Where2Place, and achieved optimal performance while preserving the model's general capabilities. We will publicly release both the training data and model weights to foster further research and development in the field of Embodied Intelligence.
Referring 3D Gaussian Splatting Segmentation (R3DGS) aims to interpret free-form language expressions and localize the corresponding 3D regions in Gaussian fields. While recent advances have introduced cross-modal alignment between language and 3D geometry, existing pipelines still struggle with cross-view consistency due to their reliance on 2D rendered pseudo supervision and view specific feature learning. In this work, we present Camera Aware Referring Field (CaRF), a fully differentiable framework that operates directly in the 3D Gaussian space and achieves multi view consistency. Specifically, CaRF introduces Gaussian Field Camera Encoding (GFCE), which incorporates camera geometry into Gaussian text interactions to explicitly model view dependent variations and enhance geometric reasoning. Building on this, In Training Paired View Supervision (ITPVS) is proposed to align per Gaussian logits across calibrated views during training, effectively mitigating single view overfitting and exposing inter view discrepancies for optimization. Extensive experiments on three representative benchmarks demonstrate that CaRF achieves average improvements of 16.8%, 4.3%, and 2.0% in mIoU over state of the art methods on the Ref LERF, LERF OVS, and 3D OVS datasets, respectively. Moreover, this work promotes more reliable and view consistent 3D scene understanding, with potential benefits for embodied AI, AR/VR interaction, and autonomous perception.