Scholar
Tianzhe Chu
Google Scholar ID: v6HphBcAAAAJ
The University of Hong Kong
Citations & Impact
Citations
483
H-index
6
i10-index
6
Publications
6
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- 1. SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training - ICML 2025
- 2. Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs - Preprint
- 3. Emergence of Segmentation with Minimalistic White-Box Transformers - CPAL 2024(Oral), NeurIPS 2023 XAI Workshop(Oral)
- 4. Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models - ICLR 2024
- 5. White-Box Transformers via Sparse Rate Reduction - NeurIPS 2023
- 6. White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? - JMLR
Research Experience
- 1. Conducted research at Berkeley
- 2. Teaching Assistant for DATA8014
Education
- 1. Ph.D. student at HKU IDS, advised by Prof. Yi Ma (Fall 2024)
- 2. B.Eng. in Computer Science (Honor) from ShanghaiTech University (graduation year not provided)
Background
- Research Interests: Data, architecture, training, and understanding of foundation models; particularly interested in empirical understanding of training (M)LLM with reinforcement learning. Conducted representation learning and interpretability research during a visit to Berkeley.
Miscellany
- From Suzhou, enjoys seasoning dishes with sweetness. Gets easily annoyed by cooking philosophies that are opposite to his.
