Scholar
Haoran Zhu
Google Scholar ID: kbxHcKEAAAAJ
New York University, PhD student at ECE department
Citations & Impact
Citations
76
H-index
4
i10-index
1
Publications
5
Co-authors
0
Publications
Resume
Academic Achievements
- AD-L-JEPA: Self-Supervised Spatial World Models with Joint Embedding Predictive Architecture for Autonomous Driving with LiDAR Data. Under Review, 2025.
- Multi-View Radar Autoencoder for Self-Supervised Automotive Radar Representation Learning. IV, 2024.
- TAME: Task Agnostic Continual Learning using Multiple Experts. CVPR Workshop, 2024.
- ERASE-Net: Efficient segmentation networks for automotive radar signals. ICRA, 2023.
- Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective. arxiv (with 50+ citations), 2023.
Research Experience
- Working as a PhD candidate at New York University, focusing on building self-supervised world models for end-to-end learning to unlock fully autonomous driving.
Education
- PhD candidate, Department of Electrical and Computer Engineering, New York University, Advisor: Prof. Anna Choromanska
Background
- Research interests: Deep learning for autonomous driving and general deep learning algorithms. Focusing on world models, self-supervised representation learning, end-to-end learning, multi-modal perception (camera, LiDAR, radar), and continual learning.
Miscellany
- Academic Service: TNNLS 2023; ICRA 2023; IROS 2022, 2024, 2025; NeurIPS 2020 Beyond Backpropagation Workshop. Teaching experience includes being a Teaching Assistant for NYU ECE 7143 Advanced Machine Learning (Spring 2021), NYU ECE 6143 Machine Learning (Fall 2020), and a Machine Learning Instructor for NYU ARISE K12 STEM Education (Fall 2021).