arXiv:2607.13621v1 Announce Type: new Abstract: Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks…
Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks a more realistic requirement: an agent often ne…
arXiv cs.AI
TIER_1English(EN)·Xinghang Li, Jun Guo, Qiwei Li, Long Qian, Hang Lai, Yueze Wang, Hongyu Yan, Jiahang Cao, Xi Chen, Jingen Qu, Jiaxi Song, Nan Sun, Hanye Zhao, Futeng Liu, Wanli Peng, Heyun Wang, Yunhong Wang, Caoyu Xia, Jack Zhao, Diyun Xiang, Hangjun Ye, Heng Qu, Huapi…·
arXiv:2607.11643v1 Announce Type: cross Abstract: Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, an…
arXiv:2607.11689v1 Announce Type: cross Abstract: Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) a…
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have advanced this goal, while World Action Models (WAMs) are particularly promising because they connect can…
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods t…
Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constraints. Existing methods t…
arXiv cs.AI
TIER_1English(EN)·Mike Roberts, Renhan Wang, Rushikesh Zawar, Rachith Dey-Prakash, Quentin Leboutet, Stephan R. Richter, Matthias M\"uller, German Ros, Rui Tang, Stefan Leutenegger, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Vladlen Koltun·
arXiv:2607.06701v1 Announce Type: cross Abstract: Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We a…
Interactive simulators have become powerful tools for training embodied agents and generating synthetic visual data, but existing photorealistic simulators suffer from limited generality, programmability, and rendering speed. We address these limitations by introducing SPEAR: A S…
arXiv:2607.03283v1 Announce Type: new Abstract: Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representati…
Automated agent architecture search demonstrates potential for improving embodied agent performance while revealing challenges related to optimization signals, local optima, and credit assignment in simulation-based training.
arXiv:2607.00029v1 Announce Type: cross Abstract: Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is non…
arXiv:2604.01001v2 Announce Type: replace-cross Abstract: We introduce EgoSim, a closed-loop egocentric world simulator that generates spatially consistent interaction videos and persistently updates the underlying 3D scene state for continuous simulation. Existing egocentric sim…
arXiv cs.AI
TIER_1English(EN)·Jinwoo Jang, Daniel J. Rho, Sihyung Yoon, Hyunsuk Cho, Honguk Woo·
arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (MoE) to this setting: routing lacks an explicit noti…
Embodied.cpp is a portable C++ runtime that enables efficient deployment of vision-language-action and world-action models across heterogeneous edge devices through modular execution layers and optimized inference.
EVA-Client is an open-source framework that unifies real-robot policy deployment, data collection, and evaluation through a component-decoupled architecture with inspectable execution workflows.
Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (MoE) to this setting: routing lacks an explicit notion of scale, preventing targeted updates at spec…
Vesta is a unified embodied generalist model that integrates localization, spatial reasoning, navigation, and long-horizon planning into a single foundation model, outperforming specialized models in both benchmark tests and real-world robotic applications.
arXiv cs.CV
TIER_1English(EN)·Xinjie Wang, Liu Liu, Taojun Ding, Andrew Choi, Chaodong Huang, Mengao Zhao, Ziang Li, Jackson Jiang, Chunlei Yu, Shengxiang Liu, Wei Xu, Zhizhong Su·
arXiv:2607.07459v1 Announce Type: cross Abstract: We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready tas…
We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready task environments remains largely manual, limiting sc…
arXiv:2607.02646v1 Announce Type: cross Abstract: We present EVA-Client, an open-source framework for deployment, data collection, and evaluation of trained manipulation policies on real robots. Sitting between a policy server and the physical hardware, EVA-Client unifies the rea…
arXiv cs.CV
TIER_1English(EN)·Yifan Li, Lichi Li, Anh Dao, Xinyu Zhou, Wenjun Huang, Tianyi Ma, Yicheng Qiao, Zheda Mai, Daeun Lee, Zichen Chen, Pan Wang, Lehan Yang, Tianlong Wang, Zhen Tan, Sheng Li, Mohit Bansal, Yang Ni, Yu Kong·
arXiv:2511.17384v2 Announce Type: replace-cross Abstract: While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household e…
Embodied AI models now span vision-language-action (VLA) models and world-action models (WAMs), but practical deployment remains fragmented across model-specific Python stacks, backend assumptions, and robot-side glue code, especially on heterogeneous edge devices. Existing infer…
Vision-language models achieve strong general perception but often struggle with the spatial reasoning required for embodied tasks. We present RoboSpatialBrain, our submission to the RoboSpatial Challenge at the Embodied Reasoning in Action Workshop, CVPR 2026, built on RoboBrain…
arXiv:2606.28804v1 Announce Type: new Abstract: Embodied World Models (EWMs) have emerged as a scalable and risk-free paradigm for advancing embodied intelligence, enabling the safety-critical evaluation of Vision-Language-Action systems. However, their reliability as evaluation …
arXiv cs.CV
TIER_1English(EN)·Xinqing Li, Xin He, Le Zhang, Min Wu, Xiaoli Li, Yun Liu·
arXiv:2510.16732v3 Announce Type: replace Abstract: 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…
Artificial intelligence has spent years learning to generate words, images and videos. Now, the industry’s attention is shifting towards “world models” – AI systems designed to simulate how the physical or digital world changes over time. While the term was originally associated …
Embodied AI offers the next computing revolution. Here's why executives should look beyond LLMs and prepare for robots that learn by interacting with the physical world.
Xiaomi releases Robotics-U0 with 38 billion parameters, the first embodied generative model handling scene generation, embodied transfer, video generation, and text-to-image in a single unified architecture.
June 2026 saw 13 new embodied AI models and world models released, tracking the shift from hardware benchmarks to software intelligence competition in embodied AI.
