Scholar
Lunjun Zhang
Google Scholar ID: OqD5GcgAAAAJ
University of Toronto
Citations & Impact
Citations
553
H-index
6
i10-index
6
Publications
10
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Selected Publications:
- - Generative Verifiers: Reward Modeling as Next-Token Prediction, ICLR 2025
- - Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion, ICLR 2024
- - Towards Unsupervised Object Detection from LiDAR Point Clouds, CVPR 2023
- - World Model as a Graph: Learning Latent Landmarks for Planning, ICML 2021 (Long Talk)
Research Experience
- Student researcher at Google DeepMind working on LLM reasoning, post-training, and eval from 2024-2025. Early employee on the founding team at self-driving startup Waabi from 2021-2024, advised by Raquel Urtasun.
Education
- Ph.D. in Computer Science at the University of Toronto, Machine Learning Group, advised by Professor Jimmy Ba. B.S. in Engineering Science at the University of Toronto, interned at Vector Institute, Mila, and Uber Advanced Technologies Group during college.
Background
- Research interests: Building general-purpose agents, with a focus on recursive self-improvement. Currently working on improving various aspects of language model reasoning and agentic capabilities. Previously worked on unsupervised learning of perception, prediction, and planning in robotics.
Miscellany
- Contact: Email / Google Scholar / LinkedIn / Twitter
