About Me
I am currently an LLM researcher at JD Explore Academy (京东探索研究院), through the TGT Program, working with Jiaqi Wang, and Nan Duan, focusing on Multimodal Understanding, Post-training (RL & SFT) and Inference Efficiency.
Previously, I was with Huawei ICT BG as a member of TopMinds program (天才少年), and received my Ph.D. from the Institute of Information Engineering, Chinese Academy of Sciences in 2024, advised by Prof. Zheng Lin
and Prof. Weiping Wang.
I have published 30+ peer-reviewed papers in top-tier AI conferences including ACL, EMNLP, ICLR, NeurIPS, ICRA, IROS, AAAI, IJCAI, MM. My open-source projects have accumulated 3000+ stars on GitHub.
We're hiring interns for the TGT program! If you have top-tier publications and are passionate about video understanding and VLMs, we'd love to hear from you.
Recent News
[2026.1] Two papers accepted to ICLR 2026.
[2025.11] Three papers accepted to AAAI 2026.
[2025.10] One papers accepted to IROS workshop 2025.
[2025.09] Two papers accepted to NeurIPS 2025.
[2025.06] Awarded Major Contribution Special Award at Huawei.
[2025.01] One paper accepted to ACL 2025.
Selected Publications
* indicates co-first author, † indicates corresponding author. Full list available on Google Scholar.
LLM Test-time Optimization
Preprint
System 1&2 Synergy via Dynamic Model Interpolation
Chenxu Yang*, Qingyi Si*, Chong Tian, Xiyu Liu, Dingyu Yao, Chuanyu Qin, Zheng Lin, Weiping Wang, Jiaqi Wang
Preprint
AAAI'26
Test-time Prompt Intervention
Chenxu Yang*, Qingyi Si*, Mz Dai*, Dingyu Yao, Mingyu Zheng, Minghui Chen, Zheng Lin, Weiping Wang
AAAI 2026
ICLR'26
Dynamic Early Exit in Reasoning Models
Chenxu Yang*, Qingyi Si*, Yongjie Duan, Zheliang Zhu, Chenyu Zhu, Qiaowei Li, Minghui Chen, Zheng Lin, Weiping Wang
ICLR 2026
Reinforcement Learning and Post-training
Preprint
Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning
Ziheng Li, Liu Kang, Feng Xiao, Luxi Xing, Qingyi Si, Zhuoran Li, Weikang Gong, Deqing Yang, Yanghua Xiao, Hongcheng Guo
Preprint
NeurIPS'25
S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
Muzhi Dai*, Chenxu Yang*, Qingyi Si†
NeurIPS 2025
NeurIPS'25 workshop
Stable Reinforcement Learning for Efficient Reasoning
Muzhi Dai*, Shixuan Liu*, Qingyi Si†
NeurIPS workshop 2025
ACL'24
Multimodal Table Understanding
Mingyu Zheng*, Xinwei Feng*, Qingyi Si*, Qiaoqiao She, Zheng Lin, Wenbin Jiang, Weiping Wang
ACL 2024
EMNLP'23
An Empirical Study of Instruction-tuning Large Language Models in Chinese
Qingyi Si*, Tong Wang*, Zheng Lin, Xu Zhang, Yanan Cao, Weiping Wang
EMNLP 2023
ACL'23
Combo of Thinking and Observing for Outside-Knowledge VQA
Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang
ACL 2023
Long/Streaming Context and Sparse Attention
ICLR'26
LouisKV: Efficient KV Cache Retrieval for Long Input-Output Sequences
Wenbo Wu*, Qingyi Si*, Xiurui Pan, Ye Wang, Jie Zhang
ICLR 2026
AAAI'26
Sparse Attention across Multiple-context KV Cache
Ziyi Cao*, Qingyi Si*, Jingbin Zhang, Bingquan Liu
AAAI 2026
ACL'25
AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding
Xiao Wang*, Qingyi Si* Shiyu Zhu, Jianlong Wu, Li Cao, Liqiang Nie
ACL 2025