Scholar
Rongzhi Zhang
Google Scholar ID: jHgmQEIAAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
447
H-index
10
i10-index
10
Publications
17
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 1. DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment (EMNLP, 2025). 2. Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only (COLM, 2025). 3. Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training (NAACL, 2025). 4. LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy (NeurIPS ML&C Workshop, 2024). 5. Aligning Large Language Models with Representation Editing: A Control Perspective (NeurIPS, 2024). 6. TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance (COLM, 2024).
Research Experience
- Research internships at Google Research, Microsoft Azure AI, and Amazon Stores Foundational AI.
Education
- 1. Georgia Institute of Technology, Ph.D. Candidate in Machine Learning (Aug. 2019 - Present), Advisor: Prof. Chao Zhang; M.S. in Electrical and Computer Engineering (May 2021). 2. Zhejiang University, B.Eng. in Measurement Control Technology and Instruments (Aug. 2015 - June 2019). 3. Harvard Medical School, Visiting Student Researcher in Neural System Group (Sep. 2018 - May 2019).
Background
- Research interest primarily lies in model efficiency and data efficiency of language models. Spent several fantastic research internships at Google Research, Microsoft Azure AI, and Amazon Stores Foundational AI.
