Oral Session 1
| Time | Title | Presenter |
|---|---|---|
| 9:00-9:10 | Region-Based Representations | Savya Khosla |
| 9:10-9:20 | Mobile Manipulation | Arjun Gupta |
| 9:20-9:30 | Versatile Video Diffusion Editor for Videos and 3D Scenes | Junkun Chen |
| 9:30-9:40 | Versatile Multimodal Learning with Less Human Supervision | Shengcao Cao |
| 9:40-9:50 | Autoregressive Generative Models | Ziqi Pang |
| 9:50-10:00 | Scalable, Physics-Driven Generation of Human-Object Interactions | Sirui Xu |
| 10:00-10:10 | Robotic Manipulation by Imitating Generated Videos with Zero Training Demos | Shivansh Patel |
| 10:10-10:20 | C3T: Cross-modal Transfer Through Time for Human Action Recognition | Abhi Kamboj |
| Coffee Break (10:20-10:30) | ||
Oral Session 2
| Time | Title | Presenter |
|---|---|---|
| 10:30-10:40 | Learning Predictive Visuomotor Coordination | Wenqi Jia |
| 10:40-10:50 | Weather simulation with video diffusion model | Chih-Hao Lin |
| 10:50-11:00 | Perceive, Simulate, Imitate: a Simple Framework for Cross-Embodiment Visual Imitation | Albert Zhai |
| 11:00-11:10 | Template Based Visual Program Distillation | Michal Shlapentokh-Rothman |
| 11:10-11:20 | LidarDM | Vlas Zyrianov |
| 11:20-11:30 | Tool-as-Interface: Learning Robot Policies from Human Tool Usage through Imitation Learning | Haonan Chen |
| 11:30-11:40 | Decomposing any image into 3D primitives with applications to controlled image synthesis | Vaibhav Vavilala |
| 11:40-11:50 | DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing | Ozgur Kara |
| 11:50-12:00 | SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images | Zixuan Huang |
| Lunch (12:00-1:15) | ||
Panel Sessions
| Time | Session | Details | Moderators |
|---|---|---|---|
| 1:15-2:00 | Faculty Panel | Discussion with faculty members | Aditya Prakash & Zhen Zhu |
| 2:00-3:00 | Alumni Panel | Discussion with program alumni | Sethuraman T V & Savya Khosla |
Oral Session 3
| Time | Title | Presenter |
|---|---|---|
| 3:10-3:20 | Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation | Bolin Lai |
| 3:20-3:30 | From physgen to physgen3d: Crafting a Miniature Interactive World from a Single Image | Shaowei Liu |
| 3:30-3:40 | Web Agents | Qianlan Yang |
| 3:40-3:50 | Unleashing Diffusion for Perception | Xin Xu |
| Posters + Discussion (3:50-5:00) | ||
Alumni Panel
Meet our Alumni who have made significant contributions to their fields.
