Kexin Huang

Kexin Huang

(黄科鑫)

PhD Student

Lab for Data Science, University of Science and Technology of China
Based in Shanghai / Beijing
Advisor: Prof. Xiangnan He and Prof. Xiang Wang
Email: huangkx AT mail.ustc.edu.cn
GitHub Google Scholar
I am currently in the 3rd year of my PhD program at USTC Lab for Data Science, supervised by Prof. Xiangnan He and Prof. Xiang Wang. My research focuses on advancing large language models (LLMs) through post-training techniques, e.g., reinforcement learning.

News

Education

University of Science and Technology of China (USTC)
PhD Candidate in School of AI and Data Science  ·  2023.09 - 2028.06 (Expected)
Advisor: Prof. Xiangnan He and Prof. Xiang Wang
University of Science and Technology of China (USTC)
Bachelor in School of Computer Sciences  ·  2019.09 - 2023.06
Advisor: Prof. Xiangnan He

Publications

2026
Experience Augmented Policy Optimization for LLM Reasoning
Jinda Lu, Kexin Huang, Junkang Wu, Shuo Yang, Jinghan Li, Chiyu Ma, Shaohang Wei, Xiang Wang, Guoyin Wang, Jingren Zhou
ICML 2026 [Page]
One-Way Policy Optimization for Self-Evolving LLMs
Shuo Yang, Jinda Lu, Kexin Huang, Chiyu Ma, Shaohang Wei, Yuyang Liu, Guoyin Wang, Jingren Zhou, Li Yuan
ICML 2026 [Page]
Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
Shuo Yang, Jinda Lu, Chiyu Ma, Kexin Huang, Haoming Meng, Qihui Zhang, Yuyang Liu, Bolin Ding, Guoyin Wang, Li Yuan, Jingren Zhou
ICML 2026 [Page]
Mitigating Reward Hacking in LLM-based Recommendation: A Preference Optimization Approach
Heyu Chen, Junkang Wu, Guoqing Hu, Kexin Huang, Xiang Wang, Jiancan Wu
ICML 2026 [Page]
Beyond Magnitude: Leveraging Direction of RLVR Updates for LLM Reasoning
Kexin Huang, Haoming Meng, Junkang Wu, Jinda Lu, Chiyu Ma, Ziqian Chen, Xue Wang, Bolin Ding, Jiancan Wu, Xiang Wang, Xiangnan He, Guoyin Wang, Jingren Zhou
ICLR 2026 [PDF] [Code]
Quantile Advantage Estimation for Entropy-Safe Reasoning
Junkang Wu, Kexin Huang, Jiancan Wu, An Zhang, Xiang Wang, Xiangnan He
ICLR 2026 [PDF] [Code]
Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
Haoming Meng, Kexin Huang, Shaohang Wei, Chiyu Ma, Shuo Yang, Xue Wang, Guoyin Wang, Bolin Ding, Jingren Zhou
ICLR 2026 [PDF]
2025
RePO: ReLU-based Preference Optimization
Junkang Wu, Kexin Huang, Xue Wang, Jinyang Gao, Bolin Ding, Jiancan Wu, Xiangnan He, Xiang Wang
NeurIPS 2025 [PDF] [Code]
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction
Jie Sun, Tianyu Zhang, Houcheng Jiang, Kexin Huang, Xiang Shu, Zhibo Zhu, Lintao Ma, Xingyu Lu, Jun Zhou, Junkang Wu, Chi Luo, An Zhang, Jiancan Wu, Xiang Wang
EMNLP 2025 (Findings) [PDF] [Code]
Larger or Smaller Reward Margins to Select Preferences for Alignment?
Kexin Huang, Junkang Wu, Ziqian Chen, Xue Wang, Jinyang Gao, Bolin Ding, Jiancan Wu, Xiangnan He, Xiang Wang
ICML 2025 [PDF] [Code]
Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response
Kexin Huang, Ziqian Chen, Xue Wang, Chongming Gao, Jinyang Gao, Bolin Ding, Xiang Wang
ICML 2025 [PDF] [Code]
SPRec: Leveraging Self-Play to Debias Preference Alignment for Large Language Model-based Recommendations
Chongming Gao, Ruijun Chen, Shuai Yuan, Kexin Huang, Yuanqing Yu, Xiangnan He
WWW 2025 (Oral) [PDF] [Code]
2024
Auctionformer: A Unified Deep Learning Algorithm for Solving Equilibrium Strategies in Auction Games
Kexin Huang, Ziqian Chen, Xue Wang, Chongming Gao, Jinyang Gao, Bolin Ding, Xiang Wang
ICML 2024 [PDF] [Code]
2023
Alleviating Matthew Effect of Offline Reinforcement Learning in Recommendation
Chongming Gao, Kexin Huang, Jiawei Chen, Yuan Zhang, Biao Li, Peng Jiang, Shiqi Wang, Zhong Zhang, Xiangnan He
SIGIR 2023 Best Paper Honorable Mention [PDF] [Code]
Learn to Explore: on Bootstrapping Interactive Data Exploration with Meta-learning
Yukun Cao, Xike Xie, Kexin Huang
ICDE 2023 [PDF]

Experiences & Services

Research Intern · Alibaba Tongyi Lab, Hangzhou
April 2023 - January 2026
- Qwen Pilot, Mentor: Guoyin Wang
- DAIL Lab, Mentor: Ziqian Chen, Xue Wang, Jinyang Gao, Bolin Ding
Teaching Assistant · Graph Theory, USTC
Fall 2022 · Teaching Professor: Yinlong Xu

Grants & Honors

NSFC Young Student Basic Research Program (PhD Student) 2026 - 2027
National Scholarship (Master) 2025
SIGIR'23 Best Paper Honorable Mention 2023