Scholar
Anthony GX-Chen
Google Scholar ID: 7jAlFsIAAAAJ
NYU
Citations & Impact
Citations
140
H-index
4
i10-index
3
Publications
11
Co-authors
20
list available
Publications
Resume (English only)
Academic Achievements
- 2025: 'KL-Regularized Reinforcement Learning is Designed to Mode Collapse', NeurIPS Workshop on Foundations of Reasoning in Language Models (accepted)
- 2025: 'Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?', Conference on Language Modelling (COLM)
- 2025: 'Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction', ICLR
- 2024: 'Testing Causal Hypotheses through Hierarchical Reinforcement Learning', NeurIPS Workshop on Intrinsically Motivated Open-ended Learning
- 2024: 'Light-weight probing of unsupervised representations for reinforcement learning', Reinforcement Learning Conference (RLC), co-authored with Yann LeCun et al.
Background
- 5th-year Ph.D. candidate at NYU's CILVR Lab and Center for Data Science
- Research focuses on understanding the reinforcement learning (RL) framework and developing better RL algorithms
- Key questions: efficient exploration and autonomous world modeling, scalable RL with minimal tricks, leveraging foundation models to discover unknowns
- Master's thesis introduced new value function decomposition methods in RL, linked to hippocampal neuroscience theories
- Undergraduate collaborations with researchers in psychiatric genomics, computational neuroscience, and theoretical neuroscience
