Haoran Zhu

I'm a postdoctoral researcher at New York University, working on world models with Prof. Yann LeCun.

My ultimate vision is to build intelligent machines for the physical world. To enable that long term vision, I'm interested in world models, self-supervised learning, and end-to-end learning.

Previously, I earned my Ph.D. from New York University as well, where I was advised by Prof. Anna Choromanska and worked on deep learning for autonomous driving.

Email / Scholar / Github / X / Linkedin

Selected Publications

AD-E2E-JEPA: A Joint-Embedding Predictive Architecture For End-to-End Autonomous Driving
Haoran Zhu, Wancong Zhang, Yann LeCun, Anna Choromanska
arxiv, 2026
arxiv / code

Zero-Shot Cross-City Generalization in End-to-End Autonomous Driving: Self-Supervised versus Supervised Representations
Fatemeh Naeinian, Ali Hamza, Haoran Zhu, Anna Choromanska
arxiv, 2026

AD-LiST-JEPA: Self-Supervised JEPA-based World Models for LiDAR Occupancy Completion and Forecasting
Haoran Zhu, Anna Choromanska
arxiv, 2026

AD-L-JEPA: Self-Supervised Representation Learning with Joint Embedding Predictive Architecture for Automotive LiDAR Object Detection
Haoran Zhu, Zhenyuan Dong^†, Kristi Topollai^†, Beiyao Sha^†, Anna Choromanska
(† denotes equal contribution as second authors.)
AAAI, 2026
project page / arxiv / code / video

Multi-View Radar Autoencoder for Self-Supervised Automotive Radar Representation Learning
Haoran Zhu, Haoze He, Anna Choromanska, Satish Ravindran, Binbin Shi, Lihui Chen
IV, 2024

TAME: Task Agnostic Continual Learning using Multiple Experts
Haoran Zhu^*, Maryam Majzoubi^*, Arihant Jain^*, Anna Choromanska
CVPR Workshop, 2024

ERASE-Net: Efficient segmentation networks for automotive radar signals
Shihong Fang, Haoran Zhu, Devansh Bisla, Anna Choromanska, Satish Ravindran, Dongyin Ren, Ryan Wu
ICRA, 2023

Design and source code from Jon Barron's website