Ce Zhang (张册)

I am a first year Ph.D. student at UNC-Chapel Hill working with Prof. Gedas Bertasius. Previously, I obtained my Master's degree from Brown Universiy advised by Prof. Chen Sun in 2023. During my Master's Program, I was also fortunate to work with Dr. Kwonjoon Lee in a project collaborated with Honda Research Institute USA. Before that, I obtained my Bachelor's degree from Southeast University in China in 2020.

I like music, sports, PC games, and watching funny videos.

Email  /  Github

profile photo

Research

I'm boradly interested in Computer Vision, Multimodal learning and Robotics. Currently, I'm mainly working on video understanding, with a focus on leveraging foundation models (LLMs, VLMs, etc.) to solve multiple video understanding tasks. I'm also interested in offline decision making, especially learning from videos. I believe the commonsense knowledge encoded in foundation models would help solve robotic tasks faster and more robustly.

clean-usnob Goal-Conditioned Predictive Coding as an Implicit Planner for Offline Reinforcement Learning
Zilai Zeng, Ce Zhang, Shijie Wang, Chen Sun
NeurIPS, 2023

We investigate if sequence modeling has the capability to condense trajectories into useful representations that can contribute to policy learning. GCPC achieves competitive performance on AntMaze, FrankaKitchen and Locomotion.

clean-usnob AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Qi Zhao*, Ce Zhang*, Shijie Wang, Changcheng Fu, Nakul Agarwal, Kwonjoon Lee, Chen Sun
arXiv, 2023

We use discretized action labels to represent videos, then feed the representations to LLMs for long-term action anticipation. Results on Ego4D, EK-55 and Gaze show that this simple approach is suprisingly effective.

clean-usnob Object-centric Video Representation for Long-term Action Anticipation
Changcheng Fu*, Ce Zhang*, Shijie Wang, Nakul Agarwal, Kwonjoon Lee, Chiho Choi, Chen Sun
In submission


This webpage is adapted from Jon Barron's page.