Schedule

Opening Remarks

Workshop Organizers

Spotlight Talks (1)

9:10 - 9:18: TD-MPC2: Scalable, Robust World Models for Continuous Control
9:18 - 9:26: ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning
9:26 - 9:34: Evaluating Robustness of Visual Representations for Object Assembly Task Requiring Spatio-Geometrical Reasoning
9:34 - 9:42: (Virtual) Diverse Offline Imitation Learning

Invited Talk: Chelsea Finn

Stanford University

Break + Poster Session

Invited Talk: Kristen Grauman

UT Austin & Meta AI

Poster Session

Lunch

Spotlight Talks (2)

1:30 - 1:38: EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning
1:38 - 1:46: NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration
1:46 - 1:54: Learning Temporal Action Abstractions as a Sequence Compression Problem
1:54 - 2:02: Learning a Structured Policy with an Implicit Value Function

Invited Talk: Vincent Vanhoucke

Robotics at Google DeepMind

Invited Talk + Discussion Session: Dhruv Batra

Georgia Tech & Meta AI

Break

Spotlight Talks (3)

4:00 - 4:08: Value Explicit Pretraining for Goal-Based Transfer Learning
4:08 - 4:16: DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models
4:16 - 4:24: Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior
4:24 - 4:32: Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos
4:32 - 4:40: VANP: Self-Supervised Vision-Action Pretraining for Navigation
4:40 - 4:48: V-Strong: Visual Traversability Learning for Off-road Navigation via Self-Supervision