Tianyu Liu

Tianyu Liu

Hi there! I am Tianyu Liu, a third-year joint Ph.D. student at USTC and Shanghai AI Laboratory, supervised by Sun Xiao.

My research interest mainly lie in efficient inference for LLM. I’m currently working on speculative decoding, a promising technique for acclerating LLM inference. I’m looking to collaborate on relative topics, mainly about inference techniques.

🔥 News

  • 2025.07:   Preprint LogitSpec to Arxiv, a training-free retrieval-based speculative decoding methods!
  • 2025.01:   PEARL is accepted to ICLR 2025!
  • 2025.01:   One paper accepted to NAACL 2025. Thanks for the carry of Qitan!
  • 2023.09:   REST is accepted to NeurIPS 2023!

📝 Publications

†: corresponding author; *:equal contribution

Preprint
sym

LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation

Tianyu Liu*, Qitan Lv*, Hao Li, Xing Gao, Xiao Sun†

[Paper]  [Code] 

ICLR 2025
sym

PEARL: Parallel Speculative Decoding with Adaptive Draft Length

Tianyu Liu, Yun Li†, Qitan Lv, Kai Liu, Jianchen Zhu, Winston Hu, Xiao Sun†

[Paper]  [Project]  [Code] 

NAACL 2025
sym

Exploiting Edited Large Language Models as General Scientific Optimizers

Qitan Lv*, Tianyu Liu*, Hong Wang†

[Paper] 

NeurIPS 2023
sym

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

Tianyu Liu, Qitan Lv, Jie Wang†, Shuling Yang, Hanzhu Chen,

[Paper]  [Code] 

📖 Educations

  • 2022.09 - Present, Ph.D. in Department of Electronic Engineering and Information Science, University of Science and Technology of China.
  • 2018.09 - 2022.06, B.Sc. in Computure Science and Technology, Central University of Finance and Economics.

🖥️ Professional Services

  • Conference reviewer for ICLR’25, WWW’25, NeurIPS’25.