Yiwei Chen
（陈一苇）

I am a first-year CS Ph.D. student focusing on Trustworthy ML and Scalable AI at Michigan State University (MSU), where my advisor is Prof. Sijia Liu. Before that, I earned both my Master's degree and Bachelor's degree from Xi’an Jiaotong University (XJTU). Also, I was admitted to the Young Gifted Program at XJTU.

Email  /  Google Scholar  /  Github  /  X  /  LinkedIn

profile photo
Research

My research interests lie at the intersection of robust and explainable artifical intelligence with the long-term goal of making AI systems safe and scalable. Currently, I'm working on:

  • Post-training of LLM, MLLM
  • Trustworthy algorithms on LLM, MLLM
  • Machine Unlearning, Safety Alignment
News
  • 2025-05 Unlearning Isn't Invisible focusing on the detecting unlearning traces in LLM from model outputs!
  • 2025-03 Safety Mirage focusing on the application of machine unlearning on VLM safety alignment, which is the first project during my PhD journey!
  • 2024-08 Started PhD journey at Michigan State University!
  • 2024-06 Graduated from Xi'an Jiaotong University!
Publications (* denotes equal contribution)
Unlearn Trace
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
Yiwei Chen*, Soumyadeep Pal*, Yimeng Zhang, Qing Qu, Sijia Liu
Under Review , 2025
Short version accepted for Oral at MUGen @ ICML'25
Code / arXiv

Large language models retain persistent fingerprints in their outputs and hidden activations even after unlearning. These traces enable detection of whether a model has been “unlearned,” exposing a new vulnerability in reverse-engineering forgotten information.

VLM Unlearn
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-tuning
Yiwei Chen*, Yuguang Yao*, Yihua Zhang, Bingquan Shen, Gaowen Liu, Sijia Liu
Under Review , 2025
Code / arXiv

Conventional supervised safety fine-tuning of VLMs suffers from the “safety mirage” problem due to training data bias, resulting in spurious correlations and over-rejections following one- word attacks. Employing unlearning algorithms on VLMs effectively removes harmful content and addresses these safety issues.

MFTR
Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer
Zhihao Zhang*, Yiwei Chen*, Weizhan Zhang, Caixia Yan, Qinghua Zheng, Qi Wang, Wangdu Chen
ACM MM , 2023
Code / arXiv

Propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer to improve the robustness of viewport prediction.