Zifan (Eric) Zhao

I'm a Research Assistant at NYU, currently working with Prof. Lerrel Pinto in the General-purpose Robotics and AI Lab (GRAIL) and Prof. Saining Xie at VISIONx. I graduated summa cum laude from NYU Shanghai with a B.S. in Computer Science. Previously, I was fortunate to be mentored by Prof. Keith Ross and Prof. Li Guo.

My research interest lies in robotics, multimodal representation learning and reinforcement learning.

Email  /  GitHub  /  LinkedIn  /  Google Scholar

profile photo

News


  • 2026-06: Cambrian-P has been accepted at ECCV 2026
  • 2026-05: Released Cambrian-P, a pose-grounded video understanding model.
  • 2025-09: ViTaL has been accepted at CoRL 2025 as a workshop best paper.
  • 2025-07: We've released ViTaL, a framework for precise, generalizable robot manipulation.
  • 2025-04: One paper has been accepted at TMLR 2025.
  • 2024-09: One paper has been accepted at NeurIPS 2024.
  • 2024-08: Our TARS robot from Interstellar took its first step! Watch here.
  • 2024-06: Invited by NYUSH AI Interest Group to give an introductory ML talk.

Publications


Cambrian-P teaser
Cambrian-P: Pose-Grounded Video Understanding
Jihan Yang*, Zifan Zhao*, Xichen Pan, Shusheng Yang, Junyi Zhang, Bingyi Kang, Hu Xu, Saining Xie
ECCV 2026
ViTaL icon
Touch begins where vision ends: Generalizable policies for contact-rich manipulation
Zifan Zhao, Siddhant Haldar, Jinda Cui, Lerrel Pinto, Raunaq Bhirangi†
CoRL 2025 Rational Robots Workshop (Best Paper)
CoRL 2025 GenPriors Workshop (Oral Presentation)
Label Smoothing icon
Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
Li Guo, Keith Ross, Zifan Zhao, George Andriopoulos, Shuyang Ling, Yufeng Xu, Zixuan Dong
TMLR 2025
Neural Collapse icon
The Prevalence of Neural Collapse in Neural Multivariate Regression
Zifan Zhao*, Li Guo*, George Andriopoulos*, Zixuan Dong*, Keith Ross*†
NeurIPS 2024

* indicates equal contribution.