Scholar
Zichong Li
Google Scholar ID: RpXgmGkAAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
503
H-index
5
i10-index
3
Publications
14
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation, Submitted to COLM 2025
- LLMs Can Generate a Better Answer by Aggregating Their Own Responses, arXiv preprint arXiv:2503.04104, 2025
- Adaptive Preference Scaling for Reinforcement Learning with Human Feedback, NeurIPS 2024
- Robust Reinforcement Learning from Corrupted Human Feedback, NeurIPS 2024
- Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process with Uncertainty Quantification, ICML 2024
- SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process, ICML 2023
- Efficient Deep Ensemble Inference via Query Difficulty-dependent Task Scheduling, ICDE 2023
- CoTel: Ontology-Neural Co-Enhanced Text Labeling, WWW 2023
- Transformer Hawkes Process, ICML 2020
Research Experience
- No specific research experience or job positions provided.
Background
- Research interests include large language models (LLMs), reinforcement learning with human feedback (RLHF), and point processes. A Ph.D. candidate at the H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, advised by Prof. Tuo Zhao.
Miscellany
- No additional personal information such as hobbies or interests provided.
Co-authors