| 8:30 am | Opening Remarks |
| 8:40 am | Invited talk 1: Bridging Language and Robotics for Interaction, Learning, and Teaching - Dorsa Sadigh (40 min) |
| 9:20 am | Invited talk 2: Building multimodal interactive agents: imitation, reinforcement learning and beyond - Chen Yan (40 min) |
| 10:00 am | Break (15 min) |
| 10:15 am | Poster Session (30 min) |
| 10:45 am | Contributed Talk 1: ScriptWorld: A Scripts-based RL Environment - Abhinav Joshi (15 min) |
| 11:00 am | Contributed Talk 2: How to Talk so AI Will Learn: Instructions, Descriptions, and Pragmatics - Ted Sumers (15 min) |
| 11:15 am | Invited Talk 3: How language generalizes experience and enables cumulative culture - Noah Goodman (40 min) |
| 11:55 am | Lunch (1h10) |
| 1:05 pm | Invited Talk 4: Towards Complex Language in Partially Observed Environments - Stefanie Tellex (40 min) |
| 1:45 pm | Contributed talk 3: Collaborating with language models for embodied reasoning - Ishita dasgupta (15 min) |
| 2:00 pm | Late Breaking Result 1: Cicero: Combining Language Models and Strategic Reasoning in the Game of Diplomacy - Adam Lerer (25 min) |
| 2:25 pm | Late Breaking Result 2: VIMA: General Robot Manipulation with Multimodal Prompts - Jim Fan (25 min) |
| 2:50 pm | Poster Session (30 min) |
| 3:20 pm | Break (15 min) |
| 3:35 pm | Invited Talk 5: Connections between Language Modeling and Reinforcement Learning - Igor Mordatch (40 min) |
| 4:15 pm | Invited Talk 6: Capturing intelligence at the level of thought - James McClelland (40 min) |
| 4:55 pm | Closing Remarks (5 min) |