I am a final-year CS Ph.D. student at University of Illinois Urbana-Champaign (UIUC), jointly advised by Prof. Jiawei Han and Prof. Hao Peng. I obtained my B.E. degree from the Department of Electronic Engineering at Tsinghua University in 2021.

Research Interests

• Large Language Model (LLM) Efficiency
• LLM Alignment

Selected Publications

• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  Suyu Ge*, Yunan Zhang*, Liyuan Liu*, Minjia Zhang, Jiawei Han, Jianfeng Gao.
  ICLR 2024 Outstanding Paper Honorable Mention

• A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
  Suyu Ge, Xihui Lin, Yunan Zhang, Jiawei Han, Hao Peng.
  ArXiv Preprint, 2024

• S2-Attention: Hardware-Aware Context Sharding Among Attention Heads
  Xihui Lin*, Yunan Zhang*, Suyu Ge, Barun Patra, Vishrav Chaudhary, Xia Song.
  ArXiv Preprint, 2024

• MART: Improving LLM Safety with Multi-Round Automatic Red-Teaming
  Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao.
  NAACL, 2024

For a full publication list, please visit my Google Scholar

Experiences

• Research Intern at NVIDIA, working on LLM alignment, 2024.01-now
• Research Intern at Meta, worked on LLM safety alignment, 2023.05-2023.12
• Research Intern at Microsoft, worked on retrieval augmented LLM, 2022.05-2022.08

Education

• Ph.D. in Computer Science, University of Illinois Urbana-Champaign, 2021-2025
• B.E. in Electronic Engineering, Tsinghua University, 2017-2021