Zhuchenyang Liu

Zhuchenyang Liu

PhD Candidate, Mobile Cloud Computing Group, Aalto University

I am a PhD candidate at Aalto University, supervised by Prof. Yu Xiao, working on Efficient and Reliable Visual Document Intelligence. I am also interested in general multimodal information understanding. I obtained a dual M.Sc. in Data Science from KTH and Aalto University with honours, and I am a Kaggle Competitions Master.

Earlier news (6)
  • Jul 2026 Giving an oral presentation at the ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS 2026) in Greece on our human-AI collaboration for sensor placement in human motion sensing work.
  • Apr 2026 Our paper on human-AI collaboration in LLM-assisted design is accepted to Proceedings of the ACM on Human-Computer Interaction.
  • Apr 2026 IKEA-Bench released — 1,623 questions benchmarking 19 VLMs on cross-depiction assembly alignment.
  • Apr 2026 Academic visit to the University of Southampton, UK.
  • Mar 2026 NanoVDR is now on HuggingFace — full datasets, models, and an online demo.
  • Oct 2025 Academic visit to TUM and LMU Munich.

Making vision-language document retrieval cheap enough to deploy, and asking what those systems ground their answers on and what their indices leak.

Inverting Multi-Vector Visual Document Indices

Zhuchenyang Liu, Yao Zhang, Yu Xiao

A multi-vector index can be inverted back into readable pages. Shuffling the vectors does not stop it, but pooled indices stay substantially harder to invert.

Preprint, Under Review

E-textile design, wearable sensing and human motion, mostly with collaborators.