About Me

I am a first-year PhD student at Purdue University, where I am fortunate to be advised by Professor Ruqi Zhang. Prior to Purdue, I received my B.S. degree from Nanjing University, where I worked closely with Professor Shujian Huang.

My research focuses on understanding and improving neural language systems. I am particularly interested in developing more efficient, capable, and reliable language models, with the goal of advancing both our theoretical understanding of these systems and their practical impact on real-world applications.

Publications

(* indicates equal contribution)

SEED: Self-Speculative Decoding via Implicit Encoder-Decoder
Hankun Lin*, Patrick Pynadath*, Ruqi Zhang.
Preprint. 2026.

Gradient-Guided Reward Optimization for Inference-time Alignment
Hankun Lin, Ruqi Zhang.
UAI 2026.
[paper] [code]

Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From
Changjiang Gao, Hankun Lin, Xin Huang, Xue Han, Junlan Feng, Chao Deng, Jiajun Chen, Shujian Huang
EMNLP 2025 (long papers).
[paper] [code]