Hengkai (Gary) Pan

I’m a MSR student at CMU RI, advised by Prof. Deepak Pathak.

Previously, I worked with Jeff Cui and Gaoyue Zhou under the supervision of Prof. Lerrel Pinto.

I work on world models and representation learning.

Email  /  Scholar  /  Twitter  /  Github

profile photo

Publications

Latent World Models Enhance Imitation Learning with Foresight
Hengkai Pan, Gaoyue Zhou, Yann LeCun, Lerrel Pinto, Deepak Pathak,
In submission, 2025  
project page
ViPRA: Video Prediction for Robot Actions
Sandeep Routray, Hengkai Pan, Unnat Jain, Shikhar Bahl, Deepak Pathak,
In submission, 2025  
project page
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
Gaoyue Zhou, Hengkai Pan, Yann LeCun, Lerrel Pinto,
ICML, 2025  
project page / arXiv / code
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
Zichen Jeff Cui, Hengkai Pan, Aadhithya Iyer, Siddhant Haldar, Lerrel Pinto,
NeurIPS, 2024  
project page / arXiv / code
Patient and lesion characteristics associated with follow-up completion for pancreatic cystic lesions detected on MRI
Chenchan Huang, Nitya L Thakore, Yiqiu Shen, Ebrahim K Rasromani, Bryce A Saba, Jonah M Levine, Sophia M Jacobi, Runhan Chen, Hengkai Pan, Stella K Kang,
Abdominal Radiology, 2025
arXiv
BURExtract-Llama: An LLM for Clinical Concept Extraction in Breast Ultrasound Reports
Yuxuan Chen, Haoyan Yang, Hengkai Pan Fardeen Siddiqui, Antonio Verdone, Qingyang Zhang, Sumit Chopra, Chen Zhao, Yiqiu Shen,
ACM Multimedia Computing for Health and Medicine, 2024
arXiv

Template From Jon Barron.
Last updated July 2025.