RePAI 2026: 1st Frontier Workshop on Representations for Physical AI
RePAI 2026 will be held in the Cross-AI Symposium 2026.
Introduction
Embodied intelligence emerges through the interaction of an agent, its body, and its environment. Advances in foundation models, generative learning, simulation, robotics, and autonomous systems are enabling increasingly capable Physical AI systems, yet the representations that support physical intelligence remain poorly understood.
The Representation for Physical AI (RePAI) workshop positions representation as a fundamental scientific problem in embodied and physical intelligence. Physical AI systems operate across levels of abstraction, from high-level semantic and task-level reasoning to real-time physical dynamics and low-level motor control. Effective representations must connect what an agent perceives with what it can predict, reason about, and change. This requires representations of objects, agents, semantics, physical properties, causality, actionable affordances, system constraints, and long-horizon consequences.
To address this challenge, RePAI brings together researchers across robotics, machine learning, computer vision, natural language processing, cognitive science, neuroscience, physics, and dynamical systems to study how representations for Physical AI are structured, grounded, learned, transformed, and evaluated for reliable interaction and action.
A central frontier of this workshop is the interface between semantic and physical intelligence: connecting data-driven foundation models with world models, predictive dynamics, planning, and classical control. RePAI also emphasizes representations that transfer across environments and embodiments and remain robust under distribution shift and physical interaction.
RePAI seeks to advance a view of embodied representation in which success is measured not only by prediction or recognition, but by the ability of representations to support generalization, intervention, planning, and reliable physical action.
Four Questions
- Represent: What should a Physical AI encode? Objects, agents, properties, relations, affordances, goals, constraints, and task structure.
- Predict: How should representations characterize change? Dynamics, causality, interaction, intervention, and possible futures.
- Reason: How should representations support inference and generalization? Abstraction, inference, planning, decision making, and compositional reasoning.
- Act: How should representations support interaction with the world? Actions, skills, feedback, control, and closed-loop behavior.
These questions connect representation across perception, prediction, reasoning, learning, and action, including the interfaces between semantic reasoning, task-level planning, physical modeling, and control.
Topics
- Physical, causal, and mechanistic representations
- Semantic, task, and language-grounded representations
- Action- and intervention-centric representations and world models
- Object-centric, relational, compositional, and hierarchical representations
- Affordances, action possibilities, skills, goals, and task representations
- Temporal, dynamical, and event-based representations
- Representations of agents, intentions, and social interaction
- Multimodal representations and language-conditioned embodied systems
- Memory, experience, and representations learned through interaction
- Representations across foundation models, world models, and physical control
- Interfaces between semantic reasoning, task-level planning, and low-level physical control
- Neural and cognitive theories of representation
- Representations grounded in physics, dynamical systems, and control
- Cross-environment and cross-embodiment representations
- Simulation-to-real transfer and representation transfer across embodiments
- Emergent, interpretable, editable, and discoverable representations
- Learning through exploration, intervention, and feedback
- Evaluation of representations beyond predictive performance
- New computational paradigms for representing and reasoning about embodied knowledge
Important Dates (AoE)
| Milestone | Cross-AI Archival Paper Deadline | Non-Archival Paper Deadline |
|---|---|---|
| Full/Short Paper Submission | October 26, 2026 | N/A |
| Poster/Demo Paper Submission | November 2, 2026 | November 16, 2026 |
| Abstract Submission | November 2, 2026 | November 16, 2026 |
| Acceptance Notification | November 16, 2026 | November 30, 2026 |
| Camera-Ready Submission | November 30, 2026 | N/A |
| Pre-Recorded Video Submission | November 30, 2026 | November 30, 2026 |
| Author Registration Deadline | December 2, 2026 | December 2, 2026 |
| Cross-AI Symposium 2026 | December 14-16, 2026 |
Archival work submissions for the Cross-AI Symposium must be submitted by the first deadline. Non-archival submissions may be submitted by either deadline.
Submission
All submissions are made through the AirBalloon conference management system and evaluated through a unified process.
1. Unpublished and Unreviewed Papers
Unpublished and unreviewed papers should follow the IEEE conference manuscript template (Overleaf or US Letter), be written in English, submitted as PDF files, and undergo double-blind review.
| Category | Length (including references) |
|---|---|
| Full paper | 8–10 pages |
| Short paper | 5–7 pages |
| Poster paper | 3–4 pages |
| Demo paper | 2–3 pages with a link to a 2-minute demo video |
| Abstract | 1 page (200-800 words) |
2. Reviewed but Not Yet Published Papers
For papers previously submitted to major AI/ML/NLP/Computer Vision/Robotics/Signal Processing/Graphics conferences (e.g., NeurIPS, ICML, ICLR, ACL, EMNLP, CVPR, ECCV, AAAI, ICRA, IROS, CoRL, SIGGRAPH, ACM MM, ICASSP), please include the original reviews as supplementary material, clearly indicating the conference, along with a separate document summarizing the revisions addressing the reviewers’ comments. This may help expedite the review process.
3. Non-Archival Submissions
Non-archival submissions may include published journal or conference papers, as well as works in progress seeking feedback. All are welcome for presentation at Cross-AI events. For published papers, authors only need to submit an abstract and the original DOI link.
4. E-Posters and Demo Videos
Electronic posters and/or demo videos are optional for all submission types (Full, Short, Poster, Demo, and Non-Archival).
| Category | Description |
|---|---|
| E-Poster | 1-page electronic poster (PDF) |
| Demo Video | up to 2-minute demo video |
5. Pre-Recorded Presentation Videos
Accepted submissions provide a pre-recorded video.
| Category | Presentation | Q&A |
|---|---|---|
| Full paper | 15 minutes | 3 minutes |
| Short paper | 10 minutes | 2 minutes |
| Poster | 6 minutes | 2 minutes |
| Demo | 5 minutes (system description + showcase) | 2 minutes |
| Abstract | 5 minutes | 2 minutes |
Publishing & Registration Requirements
All accepted archival papers will be published in the indexed Cross-AI conference proceedings. At least one author must register for the workshop. Authors may optionally have their papers considered for further publication in an IEEE-published Cross-AI Special Edition in 2027, subject to Cross-AI approval and an additional publication fee.
Media Hosting: Submitted presentation and demo videos, e-posters, audio, and other approved media will be hosted on the conference platform and made openly accessible for three years. Media hosting and open access are included in the Author registration fee.
Cross-AI Group
This group serves as a forum for notices and announcements of interest to the Cross-AI community. This includes news, events, calls for papers, calls for collaborations between academia and industry, dataset releases, employment-related announcements, etc.
Welcome to subscribe to the Cross-AI group.
If you are interested in serving on the workshop program committee or paper reviewing, please apply online.