Jiaqi W. Ma

Assistant Professor, University of Illinois Urbana-Champaign

5 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

2 papers

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining

#101 · Weiyi Wang, Junwei Deng, Yuzheng Hu, Shiyuan Zhang, Xirui Jiang, Runting Zhang, Han Zhao, Jiaqi W. Ma

We identify and address an overlooked challenge in the practical application of data attribution: hyperparameter tuning is tricky due to the costly evaluation metrics.

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

#1303 · Yiwen Tu, Pingbang Hu, Jiaqi W. Ma

We propose the a theoretical-sound machine unlearning evaluation framework with provable properties.

Poster Session 3

1 paper

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models

#111 · Cathy Jiao, Yijun Pan, Emily Xiao, Daisy Sheng, Niket Jain, Hanzhang Zhao, Ishita Dasgupta, Jiaqi W. Ma, Chenyan Xiong

Poster Session 6

2 papers

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

#104 · Yuzheng Hu, Fan Wu, Haotian Ye, David Forsyth, James Zou, Nan Jiang, Jiaqi W. Ma, Han Zhao

We propose the first framework of data attribution for online RL.

GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection

#1006 · Pingbang Hu, Joseph Melkonian, Weijing Tang, Han Zhao, Jiaqi W. Ma

Propose a scalable gradient compression algorithm for data attribution with sub-linear complexity that achieves competitive attribution results.