Yucheng Li

Researcher, Alibaba Group

Joined

November 2021

Names

Yucheng Li (Preferred)

YUCHENG LI

Emails

****@surrey.ac.uk (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Alibaba Group (alibaba-inc.com)

2025 – Present

PhD student

University of Surrey (surrey.ac.uk)

2021 – 2025

MS student

East China Normal University (ecnu.edu.cn)

2018 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

Natural Language Processing

2018 – Present

Natural Language Generation

2018 – Present

Publications

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu
- MSLD 2026 Poster
- Readers: Everyone
xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction
Chi-Chih Chang, Wei-Cheng Lin, Chien-Yu Lin, Yash Akhauri, Hung-Yueh Chiang, Xilai Dai, Huiqiang Jiang, Yucheng Li, Kai-Chiang Wu, Luis Ceze, Mohamed S. Abdelfattah
- Submitted to ICLR 2026
- Readers: Everyone
MTraining: Efficient Distributed Training for Ultra-Long Contexts via Dynamic Sparse Attention
Wenxuan Li, Chengruidong Zhang, Huiqiang Jiang, Yucheng Li, Yuqing Yang, Lili Qiu
- ES-FoMo III
- Readers: Everyone
R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu
- NeurIPS 2025 poster
- Readers: Everyone
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Zefan Cai, Yichi Zhang, Bofei Gao, Yuliang Liu, Yucheng Li, Tianyu Liu, Keming Lu, Wayne Xiong, Yue Dong, Junjie Hu, Wen Xiao
- COLM 2025
- Readers: Everyone
SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression
Yucheng Li, Surin Ahn, Huiqiang Jiang, Amir H. Abdi, Yuqing Yang, Lili Qiu
- COLM 2025
- Readers: Everyone
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention
Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu
- ICLR 2025 FM-Wild Workshop
- Readers: Everyone
Estimating Contamination via Perplexity: Quantifying Memorisation in Language Model Evaluation
Yucheng Li
- MLDPR 2025
- Readers: Everyone
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention
Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu
- ICML 2025 poster
- Readers: Everyone
SCBench: A KV Cache-Centric Analysis of Long-Context Methods
YUCHENG LI, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu
- ICLR 2025 Poster
- Readers: Everyone

View all 13 publications

Co-Authors

View all 45 co-authors