Chenxu Yang (杨晨旭)

Ph.D. candidate @ IIE, CAS | VLM & RL & Inference Efficiency

I am a Ph.D. candidate at the Institute of Information Engineering, Chinese Academy of Sciences in Beijing, advised by Prof. Zheng Lin. I am currently interning at JD Explore Academy (京东探索研究院) through the TGT Program, advised by Qingyi Si, Jiaqi Wang and Nan Duan, focusing on Multimodal Understanding, Post-training (RL), and Efficient Reasoning. I have published 20+ peer-reviewed papers in top-tier AI conferences including ICLR, NeurIPS, ACL, EMNLP, AAAI, IJCAI, and COLING (including collaborative publications), with 13 papers as first or co-first author.

Email Google Scholar Semantic Scholar GitHub
Portrait of Chenxu Yang

News

  1. Two papers accepted to IJCAI 2026.
  2. One paper accepted to ACL 2026.
  3. One paper accepted to ICLR 2026.
  4. Two papers accepted to AAAI 2026.
  5. One paper accepted to NeurIPS 2025.
  6. One paper accepted to EMNLP 2025.

First-Author Publications

* indicates co-first author, † indicates corresponding author. Full list available on Google Scholar.

Report

Report EasyVideoR1: Easier RL for Video Understanding
Chuanyu Qin*, Chenxu Yang*, Qingyi Si*, Naibin Gu*, Dingyu Yao*, Zheng Lin, Peng Fu, Nan Duan, Jiaqi Wang
Preprint
[PDF] [github] [huggingface]

Post-training

Preprint Self-Distilled RLVR
Chenxu Yang*, Chuanyu Qin*, Qingyi Si*, Minghui Chen, Naibin Gu, Dingyu Yao, Zheng Lin, Weiping Wang, Jiaqi Wang, Nan Duan
Preprint
[PDF] [github] [huggingface]
Preprint Near-Future Policy Optimization
Chuanyu Qin*, Chenxu Yang*, Qingyi Si*, Naibin Gu, Dingyu Yao, Zheng Lin, Peng Fu, Nan Duan, Jiaqi Wang
Preprint
[PDF] [huggingface]
Preprint Co-Evolving Policy Distillation
Naibin Gu*, Chenxu Yang*, Qingyi Si*, Chuanyu Qin, Dingyu Yao, Peng Fu, Zheng Lin, Weiping Wang, Nan Duan, Jiaqi Wang
Preprint
[PDF] [huggingface]
NeurIPS'25 S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models
Muzhi Dai*, Chenxu Yang*, Qingyi Si†
NeurIPS 2025
[PDF]
EMNLP'25 Weights-Rotated Preference Optimization for Large Language Models
Chenxu Yang*, Ruipeng Jia*, Mingyu Zheng, Naibin Gu, Zheng Lin, Siyuan Chen, Weichong Yin, Hua Wu, Weiping Wang
EMNLP 2025
[PDF]
IJCAI'26 Online Self-Calibration Against Hallucination in Vision-Language Models
Minghui Chen*, Chenxu Yang*, Hengjie Zhu, Dayan Wu, Zheng Lin, Qingyi Si
IJCAI 2026
[PDF]

Test-time Optimization

IJCAI'26 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
IJCAI 2026
[PDF]
AAAI'26 Test-time Prompt Intervention
Chenxu Yang*, Qingyi Si*, Mz Dai*, Dingyu Yao, Mingyu Zheng, Minghui Chen, Zheng Lin, Weiping Wang
AAAI 2026
[PDF]
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
[PDF] [Code]

Multi-turn Dialogue

AAAI'26 Oral Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models
Chenxu Yang*, Qingyi Si*, Zheng Lin
AAAI 2026 Oral
[PDF]
EMNLP'23 Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation
Chenxu Yang, Zheng Lin, Lanrui Wang, Chong Tian, Liang Pang, Jiangnan Li, Qirong Ho, Yanan Cao, Weiping Wang
EMNLP 2023
[PDF] [Code]
COLING'22 TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation
Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie Zhou
COLING 2022
[PDF] [Code]

Co-authored Papers

ACL'26 VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization
Dingyu Yao, Chenxu Yang, Zhengyang Tong, Zheng Lin, Wei Liu, Jian Luan, Weiping Wang
ACL 2026
IJCAI'25 Categorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification
Minghui Chen, Dayan Wu, Chenxu Yang, Qinghang Su, Zheng Lin
IJCAI 2025
COLING'25 Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference
Lanrui Wang, Jiangnan Li, Chenxu Yang, Zheng Lin, Hongyin Tang, Huan Liu, Yanan Cao, Jingang Wang, Weiping Wang
COLING 2025
EMNLP'22 Findings Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie Zhou
EMNLP 2022 Findings