Scholar
Zihao Tang
Google Scholar ID: YBffTgsAAAAJ
Microsoft
Citations & Impact
Citations
28
H-index
3
i10-index
1
Publications
5
Co-authors
0
Publications
Resume
Academic Achievements
- Publications:
- - Distributionally Robust Optimization For Language Modeling
- - Optimizing Language Models for Human Preferences is a Causal Inference Problem
- - Token-level Direct Preference Optimization
- - SimPO: Simple Preference Optimization with a Reference-Free Reward
- - KL Divergence: Forward vs Reverse?
Research Experience
- Internship at MSRA (Microsoft Research Asia).
Education
- Master's Degree student at Zhejiang University, advised by A.P. Kun Kuang and Prof. Fei Wu.
Background
- Research interests include Model Compression (Data-Free Knowledge Distillation, Out-of-Domain Knowledge Distillation, etc.), Domain Adaptation, and Large-Small Model Collaboration. Currently, committed to LLM (Large Language Model), especially in reinforcement learning.
Miscellany
- The personal website uses the Chirpy theme for Jekyll.