Xiaojun Quan

Full Professor, Shenzhen Loop Area Institute

Full Professor, School of Computer Science and Engineering, SUN YAT-SEN UNIVERSITY

Joined

July 2019

Names

Xiaojun Quan (Preferred)

Emails

****@i2r.a-star.edu.sg (Confirmed)

****@mail.sysu.edu.cn (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Full Professor

Shenzhen Loop Area Institute (slai.edu.cn)

2026 – Present

Full Professor

School of Computer Science and Engineering, SUN YAT-SEN UNIVERSITY (sysu.edu.cn)

2017 – 2026

Advisors, Relations & Conflicts

PhD Advisor

Wenyin Liu

2009 – 2012

Expertise

model fusion

2023 – 2025

large language models

2018 – 2025

model compression

2018 – 2025

Publications

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
Shiping Gao, Hongzhan Chen, Xiaojun Quan, Qifan Wang, Lifu Huang
- arXiv
- Readers: Everyone
Self-Evolution Fine-Tuning for Policy Optimization
Ruijun Chen, Jiehao Liang, Shiping Gao, Fanqi Wan, Xiaojun Quan
- EMNLP2024 Findings
- Readers: Everyone
SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
Ziyi Yang, Weizhou Shen, Chenliang Li, Ruijun Chen, Fanqi Wan, Ming Yan, Xiaojun Quan, Fei Huang
- ICLR 2026 Poster
- Readers: Everyone
FuseRL: Dense Preference Optimization for Heterogeneous Model Fusion
Longguang Zhong, Fanqi Wan, Ziyi Yang, Guosheng Liang, Tianyuan Shi, Xiaojun Quan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Smooth Gradients, Stable Learning: Logits Convexity for Reinforcement Learning
Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao, Xiaojun Quan, Ting Yao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Lookahead Routing for Large Language Models
Canbin Huang, Tianyuan Shi, Yuhua Zhu, Ruijun Chen, Xiaojun Quan
- NeurIPS 2025 poster
- Readers: Everyone
Probabilistic Token Alignment for Large Language Model Fusion
Runjia Zeng, James Chenhao Liang, Cheng Han, Zhiwen Cao, Jiahao Liu, Xiaojun Quan, Yingjie Victor Chen, Lifu Huang, Tong Geng, Qifan Wang, Dongfang Liu
- NeurIPS 2025 poster
- Readers: Everyone
Discriminative Policy Optimization for Token-Level Reward Models
Hongzhan Chen, Tao Yang, Shiping Gao, Ruijun Chen, Xiaojun Quan, Hongtao Tian, Ting Yao
- ICML 2025 poster
- Readers: Everyone
Advantage-Guided Distillation for Preference Alignment in Small Language Models
Shiping Gao, Fanqi Wan, Jiajian Guo, Xiaojun Quan, Qifan Wang
- ICLR 2025 Spotlight
- Readers: Everyone
Let Large Language Models Find the Data to Train Themselves
Fanqi Wan, Deng Cai, Shijue Huang, Xiaojun Quan, Mingxuan Wang
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone

View all 98 publications

Co-Authors

View all 136 co-authors