Shiyuan Sean Zhang
Hi, I am an AI Engineer living in Bellevue. My research interests include:
Data-Centric ML
Data Attribution, Data Curation/Selection, Data Compensation
Trustworthy ML
LLM/VLM Evaluation/Benchmarking, Post-training
Multimodal Intelligence
Visual Reasoning, Unified Multimodal Models
shiyuanzhang.ml AT gmail DOT com
News
2026-04
Our paper TimeCausality accepted to CVPR 2026 DataMFM Workshop! A benchmark for evaluating causal ability in the time dimension for VLMs.
2025-09
🔥 New survey paper on data attribution:
A Survey of Data Attribution: Methods, Applications, and Evaluation in the Era of Generative AI.
2025-09
One paper accepted to NeurIPS 2025.
2025-09
New preprint "Exploring Training Data Attribution under Limited Access Constraints".
[ArXiv]
2025-05
Completed my Master's degree in CS @ UIUC 🎉
2024-09
Our paper dattri accepted as a Spotlight at NeurIPS 2024!
2024-07
One paper accepted to ICML 2024 GenLaw Workshop.
2023-05
Graduated from UIUC with a B.S. in Statistics (Summa Cum Laude) 🎓