01Research Fit
Scope
Physical World Models as scalable data engines and World Action Models for embodied decision-making.
About the Workshop
Embodied AI is entering a scaling moment, but scaling embodied systems requires more than larger policies or more robot demonstrations. It requires diverse, interaction-rich, and physically grounded experience that can be generated, structured, evaluated, and reused across tasks, embodiments, and environments. This workshop explores Physical World Models as a new scaling infrastructure for embodied AI, turning human and robot experience into scalable simulation, synthetic data, predictive rollouts, and action-relevant representations.
We organize the workshop around two tightly connected directions. Physical World Models as Data Engines asks how human videos, robot demonstrations, cross-embodiment data, Real2Sim2Real pipelines, 3D/4D world generation, visuo-tactile sensing, and data-quality benchmarks can create reliable experience for robot learning. World Action Models for Embodied Decision-Making asks how video prediction, geometry grounding, latent dynamics, touch, long-horizon reasoning, policy evaluation, and self-improving agents can bridge predicted futures and executable actions in real-world embodied systems.
Topics of Interest
Topics include, but are not limited to:
Direction I — Physical World Models as Data Engines
From human and robot experience to scalable simulation, synthetic data, and evaluation.
- Learning from human videos, demonstrations, and human-object interaction: extracting task goals, object affordances, action segments, contact events, and interaction priors from in-the-wild and egocentric human demonstrations for physical world model training and robot policy learning.
- Cross-embodiment robot data scaling and transfer: building multi-robot data mixtures, shared state/action representations, embodiment-aware metadata, and action retargeting methods to transfer experience across arms, grippers, mobile manipulators, humanoids, and other robot platforms.
- Real2Sim2Real and digital twins: reconstructing editable simulation environments from real-world observations, generating controllable rollouts, and using real-world feedback to refine simulation and world models.
- 3D/4D world modeling and generation: modeling scene geometry, object states, dynamic changes, affordances, occlusions, contact regions, and uncertainty for physically grounded data generation.
- Synthetic data generation for policy learning and evaluation: generating controllable demonstrations, simulated rollouts, scene and object-state variations, initial states, rare events, failure cases, and evaluation episodes to train, stress-test, and compare robot policies.
- Visuo-tactile data generation for contact-rich manipulation: generating and annotating synchronized vision, tactile, force/torque, proprioceptive, and action signals for learning physical interactions.
- Benchmarks and evaluation protocols for world-model-generated data: measuring how synthetic data, simulated rollouts, and real-synthetic data mixtures affect downstream robot policy performance across tasks, embodiments, and sensing modalities.
Direction II — World Action Models for Embodied Decision-Making
From world prediction to action generation, policy evaluation, and autonomous learning.
- Video-based World Action Models: using video world models and video-action prediction to imagine future observations, task progress, and executable robot actions for manipulation, navigation, and whole-body control.
- Geometry-aware World Action Models: grounding action generation in 3D/4D scene structure, object states, spatial relations, point flows, contact geometry, and multi-view consistency for physically reliable embodied action.
- Latent World Action Models for efficient planning: learning compact latent dynamics, latent actions, visual subgoals, and action-conditioned representations for low-latency prediction, planning, and robot control.
- Vision-tactile World Action Models for contact-rich manipulation: coupling visual, tactile, force/torque, proprioceptive, and action representations to predict contact transitions, slip, deformation, force evolution, and corrective actions for fine manipulation.
- Long-horizon World Action Models for task-level reasoning: integrating future prediction with subgoal discovery, temporal abstraction, value estimation, risk awareness, and memory for multi-step manipulation, mobile manipulation, and embodied planning.
- Predictive policy evaluation and safety-aware action selection: using world-model rollouts to estimate success, risks, constraint violations, and failure modes before selecting reliable actions for real-world execution.
- Agentic and self-improving World Action Models: enabling embodied agents to learn from imagined rollouts, deployment feedback, interventions, failures, and recovery trajectories for autonomous data collection, policy improvement, and continual adaptation.
Invited Speakers
Jiajun Wu
Stanford University, USA
Abhinav Valada
University of Freiburg, Germany
Rudra P.K. Poudel
Toshiba Europe, UK
Hongyang Li
University of Hong Kong, China
Ding Zhao
Carnegie Mellon University, USA
Katerina Fragkiadaki
Carnegie Mellon University, USA
Program
| Time | Session |
|---|---|
| 13:00 – 13:10 | Opening Remarks — Haibao Yu |
| 13:10 – 13:40 | Keynote 1 — Jiajun Wu (Stanford University, USA) |
| 13:40 – 14:10 | Keynote 2 — Hongyang Li (University of Hong Kong, China) |
| 14:10 – 14:40 | Keynote 3 — Rudra P.K. Poudel (Toshiba Europe, UK) |
| 14:40 – 15:00 | Coffee Break and Poster Viewing |
| 15:00 – 15:30 | Keynote 4 — Abhinav Valada (University of Freiburg, Germany) |
| 15:30 – 16:00 | Keynote 5 — Ding Zhao (Carnegie Mellon University, USA) |
| 16:00 – 16:30 | Keynote 6 — Katerina Fragkiadaki (Carnegie Mellon University, USA) |
| 16:30 – 16:40 | Best Poster Award Ceremony & Winning Paper Presentation |
| 16:40 – 17:30 | Challenge Session — WorldArena Challenge 2.0 track results and winning-team presentations |
| 17:30 – 17:40 | Closing Remarks |
Call for Papers
We invite original, unpublished work on Physical World Models and World Action Models for scaling Physical AI.
Non-archival workshop
Accepted papers will not appear in the IROS proceedings, and submission does not preclude future publication at other venues.
Submission Guidelines
02Submission
Format & Review
4–8 pages, excluding references, using the IROS workshop template; double-blind review.
03Contributions
Contribution Types
Technical and position papers, datasets, benchmarks, challenge reports, and negative results; reproducible artifacts are encouraged.
04Workshop
Presentation
All accepted papers must be presented as posters, with selected papers invited for oral spotlight presentations.
Paper & Poster Timeline
Submission Deadline
Acceptance Notification
Camera-ready
Poster Session at IROS 2026
Poster Session Award
Best Poster Award
Presented during the Poster Session at IROS 2026.
$500Prize
WorldArena Challenge 2.0
Benchmarking embodied world models from perceptual quality to interactive learning and real-world manipulation. Winning teams will present their solutions during the Challenge Session.
01Perception
Video Quality Evaluation
Visual and motion quality, content consistency, physics adherence, 3D accuracy, and controllability.
02Interactive Learning
World Model as RL Environment
Whether world models can serve as interactive environments for reinforcement learning and policy optimization.
03Physical Action
Real-World WAM Manipulation
Real-world manipulation performance in tactile WAM and vision-only WAM settings.
Challenge Timeline
Competition Opens
Final Submission Deadline
Final Results Released
Challenge Session at IROS 2026
Awards
Awards are presented separately for each competition track.
Video Quality Evaluation
-
$70011st PrizeCertificate + IROS Workshop Presentation
-
$40022nd PrizeCertificate
-
$30033rd PrizeCertificate
World Model as RL Environment
-
$1,40011st PrizeCertificate + IROS Workshop Presentation
-
$80022nd PrizeCertificate
-
$60033rd PrizeCertificate
Real-World WAM Manipulation
-
$1,40011st PrizeCertificate + IROS Workshop Presentation
-
$80022nd PrizeCertificate
-
$60033rd PrizeCertificate
Organizers
Our team spans the USA, UK, Singapore, China, and UAE, combining expertise in vision, robotics, and safety validation.
Haibao Yu
Carnegie Mellon University, USA
Spatial Intelligence, Generative Simulation, Embodied AI
Dandan Zhang
Imperial College London, UK
Embodied Intelligence, Human-Robot Interaction, Medical Robotics
Lei Yang
Nanyang Technological University, Singapore
Spatial Intelligence, World Models
Weitao Zhou
Tsinghua University, China
Autonomous Driving, RL, Safety-Critical Planning
Jianing Qiu
Mohamed bin Zayed University of AI, UAE
Foundation Models, Agents, Human-AI Interaction
Jiankai Sun
Stanford University, USA
Embodied AI, Multimodal LLMs, World Models
Tianxing Chen
The University of Hong Kong, China
Embodied AI, Robot Foundation Models, Manipulation
Lan Wei
Imperial College London, UK
Diffusion-based Image Generation, VLA Models
Wen Fan
Imperial College London, UK
Vision-based Tactile Sensing, Multimodal Robotic Manipulation
Walter Zimmer
University of California, Los Angeles (UCLA), USA
Autonomous Driving, Intelligent Transportation Systems, Foundation Models
Chen Gao
Tsinghua University, China
World model, Embodied intelligence, LLM/VLM agents
Yong Li
Tsinghua University, China
Artificial intelligence, Data science
Ping Luo
The University of Hong Kong, China
Vision-Language Models, Autonomous Driving
Program Committee
Program Committee members
Yingjuan Tang
Zhengzhou University of Light Industry, China
Lingjun Zhang
Tsinghua University, China
Yuechen Luo
Tsinghua University, China
Hanwen Shen
Stevens Institute of Technology, USA
Yang Lyu
University of Michigan, USA
Yuner Zhang
Carnegie Mellon University, USA
Zuo Yushen
SimpleAI, China
Jinhao Zhang
Harbin Institute of Technology (Shenzhen), China
Sponsors
With support from our industry partners.
Get in Touch
For submission questions, sponsorship inquiries, or program updates, contact the lead organizers directly.
Venue
David L. Lawrence Convention Center
1000 Fort Duquesne Boulevard, Pittsburgh, PA 15222, United States
Held as part of IROS 2026 (September 27 – October 1, 2026). Room assignment will be announced in the official IROS program. The workshop is an in-person event.