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

See Important Dates for all paper and abstract submission deadlines.

Author and Submission Guidelines

Please follow Author and Submission Guidelines to submit your work.

If you are interested in serving on the workshop program committee or paper reviewing, please apply online.