Zexu Sun

Researcher, Baidu Search, Baidu

Joined

January 2023

Names

Zexu Sun (Preferred)

Emails

****@ruc.edu.cn (Confirmed)

Personal Links

Google Scholar

DBLP

ORCID

Career & Education History

Researcher

Baidu Search, Baidu (baidu.com)

2025 – 2027

PhD student

Gaoling School of Artificial Intelligence, Renmin University of China (ruc.edu.cn)

2021 – 2025

Advisors, Relations & Conflicts

PhD Advisor

Xu Chen

2021 – 2025

Expertise

Causal Inference

Reinforcement Learning

Large Language model

2021 – 2024

Publications

Beyond Step Pruning: Information Theory Based Step-level Optimization for Self-Refining Large Language Models
Jinman Zhao, Erxue Min, Hui Wu, Ziheng Li, Zexu Sun, Hengyi Cai, Shuaiqiang Wang, Xu Chen, Gerald Penn
- AAAI 2026
- Readers: Everyone
Generalized Encouragement-Based Instrumental Variables for Counterfactual Regression
Yingrong Wang, Anpeng Wu, Yi He, Baohong Li, Zexu Sun, Ruoxuan Xiong, Fei Wu, Kun Kuang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
Yongcheng Zeng, Zexu Sun, Bokai Ji, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Haifeng Zhang, Xu Chen, Jun Wang
- ICLR 2026 Poster
- Readers: Everyone
Prompt and Parameter Co-Optimization for Large Language Models
Xiaohe Bo, Rui Li, Zexu Sun, Quanyu Dai, Zeyu Zhang, Zihang Tian, Xu Chen, Zhenhua Dong
- ICLR 2026 Poster
- Readers: Everyone
Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning
Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao, Bokai Ji, Xu Chen
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Ziheng Li, Zexu Sun, Jinman Zhao, Erxue Min, Yongcheng Zeng, Hui Wu, Hengyi Cai, Shuaiqiang Wang, Xu Chen, Zhi-Hong Deng, Dawei Yin
- Submitted to ICLR 2026
- Readers: Everyone
Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference Optimization
Yongcheng Zeng, Xinyu Cui, Xuanfa Jin, Qirui Mi, Guoqing Liu, Zexu Sun, Mengyue Yang, Dong Li, Weiyu Ma, Ning Yang, Jian Zhao, Jianye HAO, Haifeng Zhang, Jun Wang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
Heyang Gao, Zexu Sun, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Xu Chen
- ICLR 2026 Poster
- Readers: Everyone
Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning
Yiju Guo, Wenkai Yang, Zexu Sun, Ning Ding, Zhiyuan Liu, Yankai Lin
- NeurIPS 2025 poster
- Readers: Everyone
What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models
Qiyuan Zhang, Fuyuan Lyu, Zexu Sun, Lei Wang, Weixu Zhang, Zhihan Guo, Yufei Wang, Irwin King, Xue Liu, Chen Ma
- CoRR 2025
- Readers: Everyone

View all 28 publications

Co-Authors

View all 82 co-authors