Minds live in bodies, and bodies move through a changing world. The goal of embodied artificial intelligence is to create agents, such as robots, which learn to creatively solve challenging tasks requiring interaction with the environment. While this is a tall order, fantastic advances in deep learning, the explosive growth of large language models, and the increasing availability of large datasets like ImageNet have enabled superhuman performance on a variety of AI tasks previously thought intractable. Computer vision, speech recognition and natural language processing have experienced transformative revolutions at passive input-output tasks like language translation and image processing, and reinforcement learning has similarly achieved world-class performance at interactive tasks like games. These advances have supercharged embodied AI, enabling a growing collection of researchers to make rapid progress towards intelligent agents which can:

• See: perceive their environment through vision or other senses.
• Talk: hold a natural language dialog grounded in their environment.
• Listen: understand and react to audio input anywhere in a scene.
• Act: navigate and interact with their environment to accomplish goals.
• Reason: consider and plan for the long-term consequences of their actions.

The goal of the Embodied AI workshop is to bring together researchers from computer vision, language, graphics, and robotics to share and discuss the latest advances in embodied intelligent agents. EAI 2026’s overaching theme is World Models for Embodied AI: embodied AI agents that create models of the world to help them imagine and act, or to help researchers to test and evaluate them. This umbrella theme is divided into three topics:

• World Models for Action and Evaluation Explores both dynamics models which incorporate physics and geometry, and video models where dynamics are implicit.
• The Resurgence of Classic Methods Examining new applications of techniques such as reinforcement learning and model-predictive control to embodied AI.
• Long-Horizon Embodied Intelligence Explores benchmarks and methods for multi-step tasks, robust testing, and, in particular, safe operation.

The Embodied AI 2026 workshop will be held in conjunction with CVPR 2026 in Denver, Colorado. It will feature a host of invited talks covering a variety of topics in Embodied AI, many exciting Embodied AI challenges, a poster session, and panel discussions. The Embodied AI workshop will be held in-person with remote options on June TBDth from 8:30 to 5:30 CDT:

• In-Person: Workshop talks and panels will be held in room TBD from 8:30-noon and 1:30-5:30 CDT.
• Remote: Zoom info for remote CVPR attendees can be found on our official CVPR workshop page when it becomes available.
• Questions: We will have a microphone; also questions (in-person or remote) can be asked via Slack at:
  Ask questions on Slack
• Posters: Posters will be in TBDD from 12:00 PM to 1:30 PM CDT at boards TBD. Oral presentations will be in room TBD from TBD CDT.
• Printing: Information on poster printing will be available on CVPR's website.

• Workshop Talks: 8:30AM-5:30PM CDT - Room TBD
• Poster Session: 12:00PM-1:30PM CDT - TBD boards TBD

Ask questions on Slack

The Embodied AI 2026 workshop is hosting many exciting challenges covering a wide range of topics. More details regarding data, submission instructions, and timelines can be found on the individual challenge websites.

The workshop organizers will award each first-prize challenge winner a cash prize, sponsored by Logical Robotics and our other sponsors.

Challenge winners may be given the opportunity to present during their challenge's presentation at the workshop. Since many challenges can be grouped into similar tasks, we encourage participants to submit models to more than 1 challenge. The table below describes, compares, and links each challenge.

We invite high-quality 2-page extended abstracts on embodied AI, especially in areas relevant to the themes of this year's workshop:

• Embodied AI Solutions
• Advances in Simulation
• Generative Methods for Embodied AI
• Foundation Models

• Visual Navigation
• Embodied Mobile Manipulation
• Embodied Question Answering
• Embodied Vision & Language
• Language Model Planning

The submission deadline will close in May ( Anywhere on Earth - for clarity, 00:01 in GMT as computed by OpenReview). Papers should be no longer than 2 pages (excluding references) and styled in the CVPR format.

• Paper submissions will close in May 2026.
• Notifications will be sent in June 2026.
• Camera-ready copies of accepted papers will be due in June 2026.

Note. The order of the papers is randomized each time the page is refreshed.

The Embodied AI 2025 Workshop is sponsored by the following organizations:

Anthony Francis
Logical Robotics

David Hall
CSIRO

German Ros
NVIDIA

Mike Roberts
Adobe

Minyoung Hwang
MIT

Oleksandr Maksymets
Meta AI

Rachith Prakash
Intel

Ran Gong
UCLA

Vivan Amin
Microsoft

Coming soon...

Ade Famoti
Microsoft

Claudia Pérez D’Arpino
NVIDIA

Peyman Moghadam
CSIRO

Roberto Martín-Martín
Stanford