The Conference on Robot Learning (CoRL) runs from November 9 to 12, 2026, in Austin, Texas. Researchers from BAIR, including faculty, postdocs, and students, will present papers and participate in sessions. Professor Negar Mehr delivers an Early Career Keynote. The full schedule follows.
Conference statistics
The event hosts 33 main-conference papers, four late-breaking results (LBR) posters, and 10 oral presentations or spotlights across four days.
Schedule overview
Main conference sessions occur on November 9, 10, and 11. Workshops are scheduled for November 12.
Monday, November 9
The day opens with a spotlight session on generalist policies, memory, and transfer. This includes a paper on multi-scale embodied memory for vision language action models. Another spotlight covers diagnosing compositional generalization in sequential robot tasks. Both papers are also presented at Poster Session I between 5:00 and 6:30 PM at the JW Marriott.
Late-breaking results
Four late-breaking result posters feature Berkeley authors. These sessions are listed under the Agentic Robotics track. Topics include scaling online exploration for robot agents, guided self-improvement for embodied agents, and agentic robotics self-learning for flipping objects. The list of posters may grow as more late-breaking results are confirmed.
Keynote
Professor Negar Mehr presents the Early Career Keynote II. Her talk is titled “How Can Robots Learn to Interact and Coordinate with Others?”. Ken Goldberg chairs the session.
Poster sessions
Poster Session I takes place at the JW Marriott from 5:00 to 6:30 PM. Papers include:
- MEM: Multi-Scale Embodied Memory for Vision Language Action Models
- Large Video Planner Enables Generalizable Robot Control
- How to Peel with a Knife: Aligning Fine-Grained Manipulation with Human Preference
- HiRE: Hindsight Reward Editing for Policy Finetuning
- Scalable Behavior Cloning with Open Data, Training, and Evaluation
- Diagnosing Compositional Generalization in Sequential Robot Tasks
- AsyncVL
What it means
The schedule confirms the presence of BAIR researchers at CoRL 2026, highlighting specific contributions to robot learning, memory systems, and agentic robotics.
