Frontier Sessions
To be announced.
Keynote and invited speakers for Cross-AI 2027 will be announced here.
Speakers are selected to span the eight Cross-AI Topics rather than to represent a single field.
layout: standalone title: “REI 2026 — 1st International Workshop on Representations for Embodied Intelligence” rail: “Workshop” footer_note: “REI 2026 · Cross-AI Pre-Conference Symposium 2026”
hero_eyebrow: “Workshop at Cross-AI Pre-Conference Symposium 2026” hero_title: “REI 2026” hero_meta:
- “1st International Workshop on Representations for Embodied Intelligence”
- “December 14-16, 2026 · Online” hero_slot: “event-rei-2026” hero_ctas:
- label: “Submit a paper →” url: “#submission”
- label: “Important dates” url: “#important-dates”
6th International Workshop on Representations for Embodied Intelligence
REI 2026 will be held in the Cross-AI Pre-Conference Symposium 2026.
Introduction
Embodied intelligence emerges through the interaction of an agent, its body, and its environment. Recent advances in foundation models, generative learning, simulation, robotics, and autonomous systems have enabled increasingly capable embodied agents. Yet a fundamental scientific question remains.
What representations enable embodied agents to perceive, reason about, predict, and act in the physical world?
REI positions representation as a fundamental scientific problem in embodied intelligence. Embodied systems operate across multiple levels of abstraction, from semantic and task-level reasoning to physical dynamics and low-level control. Representations must therefore capture not only what exists and what happens, but also what matters, what can change, what causes change, what actions are possible, and how actions transform the physical world.
Such representations may support or connect diverse computational components, including foundation models, language models, world models, learned simulators, planners, policies, and physics-based controllers. REI brings together perspectives from robotics, machine learning, computer vision, language, cognitive science, neuroscience, physics, dynamical systems, and control to study how representations are structured, grounded, acquired, transformed, and used across these levels.
Four Questions
- Represent: What should an embodied agent 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 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 learning through interaction
- Foundation models, language models, world models, learned simulators, planners, policies, and controllers
- Interfaces between high-level reasoning 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 embodied knowledge
Important Dates (AoE)
| Date | Milestone |
|---|---|
| October 26, 2026 | Full paper submission (8–10 pages) |
| October 26, 2026 | Short paper submission (5–7 pages) |
| November 2, 2026 | Poster paper submission (3–4 pages) |
| November 16, 2026 | Acceptance notification |
| November 30, 2026 | Video submission |
| November 30, 2026 | Camera-ready submission deadline |
| November 30, 2026 | Author registration deadline |
| December 14-16, 2026 | Cross-AI Pre-Conference Symposium |
Submission
1. Papers
Papers follow the IEEE conference manuscript templates (Overleaf or US Letter), in English, as PDF, and are reviewed double-blind.
| Category | Length (including references) |
|---|---|
| Full paper | 8–10 pages |
| Short paper | 5–7 pages |
| Poster paper | 3–4 pages |
2. 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 |
All submissions are made through the AirBalloon conference management system and evaluated through a unified process. All accepted 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.
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.