GRASP Laboratory at CVPR 2026

8:00 AM to 1:00 PM

The 5th Explainable AI for Computer Vision (XAI4CV) Workshop at CVPR 2026

Accepted Paper, Non-Proceedings Track:

Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification

Nghia Nguyen, Tianjiao Ding, and Rene Vidal

8:25 AM to 12:30 PM

AI for Content Creation Workshop

Organizer: Lingjie Liu

9:00 AM to 5:30 PM

From Labs to Life: Embodied Intelligence in the Wild CVPR 2026 Workshop

Organizer: Lingjie Liu

1:35 PM to 2:05 PM

The 3rd Workshop on Efficient and On-Device Generation (EDGE)

Invited Speaker: Jiatao Gu

“Are Normalizing Flows Good Candidates for Interactive World Models?”

2:30 PM to 3:00 PM

The 5th Workshop on Transformers for Vision and Multimodal AI (T4V)

Invited Speaker: Jiatao Gu

3:15 PM to 3:45 PM

Sense of Space: Multi-Sensory Modeling for Embodied Intelligence

Keynote Speaker: Lingjie Liu

3:40 PM to 4:30 PM

From Labs to Life: Embodied Intelligence in the Wild CVPR 2026 Workshop

Invited Speaker: Jiatao Gu

“Should Embodied Intelligence Care About 3D?”

4:00 PM to 4:30 PM

12th CVPR Workshop on Medical Computer Vision

Keynote Speaker: René Vidal

“Trustworthy AI in Health: Foundation Models for Radiology, Cardiology and Autism Diagnosis”

8:45 AM to 5:00 PM

4th Workshop on Generative Models for Computer Vision

Best Paper Award! Accepted Paper:

FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

Wei Cao (University of Illinois Urbana-Champaign), Hao Zhang (University of Illinois Urbana-Champaign), Fengrui Tian, Yulun Wu (University of Illinois Urbana-Champaign), Yingying Li (University of Illinois Urbana-Champaign), Shenlong Wang (University of Illinois Urbana-Champaign), Ning Yu (Eyeline Labs), and Yaoyao Liu (University of Illinois Urbana-Champaign)

9:00 AM to 5:00 PM

Third Workshop on Visual Concepts

Accepted Paper:

Entropy-based Patchification Creates Semantic Tokens

Suhao Yu, Jingjia Peng, Yao Tang, and Jiatao Gu

11:00 AM to 11:40 AM

2nd Workshop on Knowledge-Intensive Multimodal Reasoning

Invited Speaker: Jiatao Gu

“Reasoning in Continuous Space”

11:15 AM to 11:45 AM

CVPR 2026 Workshop on 3D Scene Understanding for Vision, Graphics, and Robotics

Invited Speaker: Lingjie Liu

1:00 PM to 6:00 PM

2nd 4D Vision Workshop Modeling the Dynamic World

Oral Session Accepted Paper:

FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

Wei Cao (University of Illinois Urbana-Champaign), Hao Zhang (University of Illinois Urbana-Champaign), Fengrui Tian, Yulun Wu (University of Illinois Urbana-Champaign), Yingying Li (University of Illinois Urbana-Champaign), Shenlong Wang (University of Illinois Urbana-Champaign), Ning Yu (Eyeline Labs), and Yaoyao Liu (University of Illinois Urbana-Champaign)

Accepted Paper:

PointAction: 3D Points as Universal Action Representations for Robot Control

Mutian Tong, Han Jiang, Qiao Feng, Lingjie Liu, and Jiatao Gu

1:00 PM to 6:00 PM

Foundation Models Meet Embodied Agents

Organizer: Jiatao Gu

1:00 PM to 6:00 PM

4D World Models: Bridging Generation and Reconstruction

Organizer: Lingjie Liu

4:00 PM to 4:30 PM

The Seventh Annual Embodied Artificial Intelligence Workshop

Invited Speaker: Dinesh Jayaraman

“Coding Agent-Driven Robot Learning”

10:45 AM to 12:45 PM

Poster Session 1

Hierarchical Concept Embedding & Pursuit for Interpretable Image Classification

Nghia Nguyen, Tianjiao Ding, and René Vidal

4:00 PM to 6:00 PM

Poster Session 2

Highlighted Paper

STARFlow-V: End-to-End Video Generative Modeling with Autoregressive Normalizing Flows

Jiatao Gu, Ying Shen (Apple), Tianrong Chen (Apple), Laurent Dinh (Apple), Yuyang Wang (Apple), Miguel Angel Bautista (Apple), David Berthelot (Apple), Josh Susskind (Apple), and Shuangfei Zhai (Apple)

11:45 AM to 1:45 PM

Poster Session 3

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

Jinqi Luo, Jinyu Yang (Amazon), Tal Neiman (Amazon), Lei Fan (Amazon), Bing Yin (Amazon), Son Tran (Amazon), Muburak Shah (Amazon, University of Central Florida), and René Vidal

11:45 AM to 1:45 PM

Poster Session 3

Highlighted Paper

UniPixie: Unified and Probabilistic 3D Physics Learning via Flow Matching

Qilin Huang (University of Pennsylvania, Southern University of Science and Technology), Quynh Anh Huynh, Long Le, Chen Wang, Chuhao Chen, Ryan Lucas (MIT), Eric Eaton, and Lingjie Liu

11:45 AM to 1:45 PM

Poster Session 3

Next-Scale Autoregressive Models for Text-to-Motion Generation

Zhiwei Zheng, Shibo Jin, Lingjie Liu, and Mingmin Zhao

4:45 PM to 6:45 PM

Poster Session 4

Vibe Spaces for Creatively Connecting and Expressing Visual Concepts

Huzheng Yang, Katherine Xu, Andrew Lu, Michael D. Grossberg (CUNY), Yutong Bai (UC Berkeley), and Jianbo Shi

4:45 PM to 6:45 PM

Poster Session 4

Scaling Spatial and Temporal Context for Robotic Imitation Learning Policies With Scene Graphs

Jianing Qian, Qinhe Peng, Emmanuel Panov (RAI Institute), Leonor Fermoselle (RAI Institute), Dinesh Jayaraman, Bernadette Bucher (University of Michigan), and Tarik Kelestemur (RAI Institute)

3:30 PM to 5:30 PM

Poster Session 6

ActiveGrasp: Information-Guided Active Grasping with Calibrated Energy-based Model

Boshu Lei, Wen Jiang, and Kostas Daniilidis

3:30 PM to 5:30 PM

Poster Session 6

Highlighted Paper

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Chen Wang, Hao Tan (Adobe Research), Wang Yifan (Adobe Research), Zhiqin Chen (Adobe Research), Yuheng Liu (UCI), Kalyan Sunkavalli (Adobe Research), Sai Bi (Adobe Research), Lingjie Liu, and Yiwei Hu (Adobe Research)