Scholar
Hanlin Zhang
Google Scholar ID: h5IXxToAAAAJ
Harvard University
Citations & Impact
Citations
1,092
H-index
14
i10-index
16
Publications
20
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning. Preprint, 2025.
- EvoLM: In Search of Lost Language Model Training Dynamics. NeurIPS, 2025 (Oral).
- How Does Critical Batch Size Scale in Pre-training? ICLR, 2025.
- Watermarks in the Sand: Impossibility of Strong Watermarking for Generative Models. ICML, 2024.
- Improved Logical Reasoning of Language Models via Differentiable Symbolic Programming. Findings of ACL, 2023.
- Towards Principled Disentanglement for Domain Generalization. CVPR, 2022 (Oral).
- Theme by orderedlist.
Research Experience
- Involved in various research projects on language models, causal representation learning, evolutionary algorithms, etc.
Education
- Received Master's degree in Machine Learning from CMU, advised by Eric Xing; currently pursuing a PhD at Harvard, advised by Sham Kakade.
Background
- CS PhD candidate at Harvard, interested in the scientific foundations and social implications of AI.
