We present Scene2Demo, an automated framework for offline embodied data generation. Given a single RGB scene image and a user query, Scene2Demo constructs an interactive simulated scene and generates executable task configurations, primitive action flows, multi-view execution videos, and offline robot-learning datasets. Its five role-specialized generation modules perform task understanding, symbolic decomposition, BDDL configuration generation, object-size adjustment, and action-flow planning. The resulting object-centric task specifications and action transitions are organized as path search over a scene-conditioned object-action graph. Failed or incomplete executions are refined by two feedback agents: a Robotic Safety Inspector that produces step-wise visual critiques and a Robotic Task Supervisor that revises action sequences or parameters using the rollout and previous evolution history. Across 102 automatically generated primitive scene-task pairs, Scene2Demo achieves a 71.6% execution success rate; on four representative long-horizon tasks, feedback-driven refinement improves both task success and subtask-level execution quality over primitive-only execution. Comparisons with RoboGen and GenSim2 show stronger execution performance under automated data-generation settings. Finally, behavior cloning policies achieve 96.0% and 92.0% success on two representative tasks, showing that the generated data supports downstream policy learning. Our project page is available at https://scene2demo-anon.github.io/.
Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
Tianjin University(天津大学);Huawei Noah’s Ark Lab(华为诺亚实验室);Shanghai Jiao Tong University(上海交通大学);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Sun Yat-sen University(中山大学);PengCheng Laboratory(鹏城实验室);Tongji University(同济大学);University College London(伦敦大学学院);Peking University(北京大学);Tsinghua University(清华大学);Imperial College London(伦敦帝国学院);King’s College London(伦敦国王学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Manchester(曼彻斯特大学);Nanjing University(南京大学);TU Darmstadt(图宾根大学)
Self-Evolving Cognitive Framework via Causal World Modeling for Embodied Scientific Intelligence
Graduate School of Advanced Science and Engineering, Hiroshima University(广岛大学先进科学与工程研究生院);Advanced Intelligence and Robotics Research Center, Brain Science Institute, Tamagawa University(玉川大学脑科学研究所先进智能与机器人研究中心)
X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
SKL-MAIS, Institute of Automation, Chinese Academy of Sciences(SKL-MAIS,自动化研究所,中国科学院);School of Artificial Intelligence, University of Chinese Academy of Sciences(人工智能学院,中国科学院大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院);BeingBeyond;School of Computer Science, Peking University(北京大学计算机学院)
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University, Beijing, 100084, China(计算机科学与技术系,人工智能研究院,清华-博世联合机器学习中心,THBI实验室,BNRist中心,清华大学,北京,100084,中国);Peng Cheng Laboratory, 518108, China(鹏城实验室,518108,中国)
CometVLA: Co-Training on an Embodied Data Pyramid towards Physical Understanding
JD Explore Academy(京东探索研究院);School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);South China University of Technology(华南理工大学);Sun Yat-sen University(中山大学);School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)人工智能学院)
ERRA: An Embodied Representation and Reasoning Architecture for Long-horizon Language-conditioned Manipulation Tasks
The Hong Kong University of Science and Technology(香港科技大学);HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute(香港科技大学深港协同创新研究院);Monash University(莫纳什大学)
One Word, Different Action: A Real-Robot Benchmark for Language-Conditioned Embodied Reasoning
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);Shenzhen Research Institute of Big Data (SRIBD)(深圳大数据研究院)
该研究推出真实机器人基准One Word, Different Action,评估具身系统的决策不变性与敏感性,发现现代模型在多任务约束整合为机器人动作时存在明显退化,核心挑战是组合多任务需求为正确决策。
Evolving embodied intelligence from materials to machines
The Commonwealth Scientific and Industrial Research Organisation (CSIRO)(联邦科学与工业研究组织(CSIRO));Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Inria(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);Université de Lorraine(洛林大学);La Trobe University(拉筹伯大学);Monash University(莫纳什大学)
Robo-Cortex: A Self-Evolving Embodied Agent via Dual-Grain Cognitive Memory and Autonomous Knowledge Induction
The Hong Kong University of Science and Technology(香港科学与技术大学);X-Humanoid;Institute of Automation, CAS(中国科学院自动化研究所);Beijing University of Aeronautics and Astronautics(北京航空航天大学)
Universal Actions for Enhanced Embodied Foundation Models
AIR, Tsinghua University(清华大学AIR);Sensetime Research(商汤科技研究院);Peking University(北京大学);Beijing University of Posts and Telecommunications(北京邮电大学);Shanghai AI Lab(上海人工智能实验室);BAAI(北京智源人工智能研究院)
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);AiRiA;Nanjing University of Information Science and Technology(南京信息科学技术大学)
KineWorld: Action-Induced Transport Fields for Embodied World Modeling
Nanyang Technological University(南洋理工大学);North University of China(中北大学);Psibot;The Hong Kong Polytechnic University(香港理工大学);China Academy of Information and Communications Technology(中国信息通信研究院);University of Hong Kong(香港大学);Peking University(北京大学)
SpaceMind: A Modular and Self-Evolving Embodied Vision-Language Agent Framework for Autonomous On-orbit Servicing
University of Chinese Academy of Sciences(中国科学院大学);Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences(中国科学院空间利用技术与工程中心)