Hello, I'm

Zirui Li 李梓睿

I am a first year Ph.D student in Computer Science at Harbin Institute of Technology, Shenzhen, supervised by Prof. Xuefeng Bai and Prof. Kehai Chen. My current research interests include LLM reasoning, interpretability, and Latent Chain-of-Thought.

Natural Language Processing LLM reasoning Latent Chain-of-Thought LLM interpretability Multimodal LLM
Location Shenzhen, China
Portrait of Zirui Li at Park Güell, Barcelona

Research

DocMMIR: A Framework for Document Multi-modal Information Retrieval

Zirui Li, Siwei Wu, Yizhi Li, Xingyu Wang, Yi Zhou, Chenghua Lin
EMNLP 2025 Findings

Dynamics Within Latent Chain-of-Thought

Zirui Li, Xuefeng Bai, Kehai Chen, Yizhi Li, Jian Yang, Chenghua Lin, Min Zhang
ICML 2026

Education

Harbin Institute of Technology, Shenzhen

Sep 2025 - present

P.hD in Computer Science

Natural Language Processing Machine translation LLM reasoning LLM interpretability

University of Manchester

Sep 2021 - Jun 2025

M.Eng Computer Science (2:1)

Natural Language Understanding Database Design Software Engineering Game Theory Algorithms Python PyTorch Java JavaScript SQL Flask Django Linux

Beyond Code

Photography keeps my design instincts sharp.

I tell stories through lenses, experimenting with composition and post-processing to uncover new perspectives. Visual storytelling feeds directly into the way I craft thoughtful, human products.

Browse my photography journal for curated sets blending light, color, and narrative.

Experience

University of Manchester

Jun 2024 - Present

Research Intern - Chenghua Lin's research group

  • Designed DocMMIR, a document multimodal retrieval benchmark that unifies Wikipedia-scale imagery with text.
  • Built PyTorch Lightning pipelines and fine-tuned CLIP, BLIP2, SIGLIP and more MLLMs for cross-modal alignment.
  • Preprocessed 300k+ image-text samples and crafted contrastive objectives for query-to-document mapping.
  • Accepted for EMNLP2025 findings as the first author

AutoBizLine Inc.

Aug 2023 - Sep 2024

Full-stack Engineer - MySecondLine

  • Shipped 8k+ lines across a Django + JavaScript product, modernising messaging flows and dashboards.
  • Automated regulatory review pipelines with compliance tooling tailored to business rules.
  • Implemented geo-aware tax computation supporting 200+ scenarios to streamline onboarding.