Hello, I'm

Zirui Li 李梓睿

Computer Science PhD student blending Natural Language Processing, especially in multimodal LLM research, mechanism interpretability, and LLM reasoning.

Multimodal LLM Natural Language Processing LLM interpretability LLM reasoning
Location Shenzhen, China
Portrait of Zirui Li
Hugging Face
LinkedIn
GitHub
Instagram

Education

Harbin Institute of Technology, Shenzhen

Sep 2025 - present

P.hD in Computer Science

Natural Language Processing Machine translation LLM reasoning LLM interpretability Multimodal LLM

University of Manchester

Sep 2021 - Jun 2025

M.Eng Computer Science (2:1)

Exploring how language understanding, data infrastructure, and product thinking intersect to build experiences that feel effortless and human.

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

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.

Projects

Selected builds that flex analytical and product muscles.

Social Network Analysis

Sep 2023 - Apr 2024
  • Modelled networks with 15k+ nodes using NetworkX to surface influence through centrality metrics.
  • Benchmarked link prediction algorithms including Common Neighbours, Jaccard, graph autoencoders, and node2vec.

Eventlite

Jan 2023 - Apr 2023
  • Delivered a Spring Boot event platform with registration, creation workflows, and robust MVC testing.

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.