Sijia Liu
Scholar

Sijia Liu

Google Scholar ID: C7dO_UgAAAAJ
Red Cedar Distinguished Associate Professor, Michigan State Univ.; Affiliate Prof., IBM Research
Adversarial RobustnessMachine UnlearningAI SafetyBlack-box OptimizationSignal Processing
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
12,156
 
H-index
56
 
i10-index
162
 
Publications
20
 
Co-authors
20
list available
Contact
TwitterOpen ↗GitHubOpen ↗
Publications
19 items
Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
2026
Cited
0
Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
2026
Cited
0
Test-Time Unlearning via Sparse Autoencoder
2026
Cited
0
When Retain Constraints Conflict: Mitigating Forget-Retain Interference in Tabular Data
2026
Cited
0
HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety
2026
Cited
0
Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
2026
Cited
0
Stochastic Meta-Unlearning: Bridging Language Backbone and Multimodal Unlearning
2026
Cited
0
UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma
2026
Cited
0
Co-authors
19 total
Pin-Yu Chen
Pin-Yu Chen
Principal Research Scientist, IBM Research AI; MIT-IBM Watson AI Lab; RPI-IBM AIRC
Yanzhi Wang
Yanzhi Wang
Northeastern University
Yihua Zhang
Yihua Zhang
Ph.D. Student, Michigan State University
Xue Lin
Xue Lin
Northeastern University
Shiyu Chang
Shiyu Chang
University of California, Santa Barbara
Mingyi Hong
Mingyi Hong
Associate Professor, University of Minnesota; Amazon AGI
Jinghan Jia
Jinghan Jia
Michigan State University
Yuguang Yao
Yuguang Yao
Intuit