Publications

A collection of my research work. * denotes equal contribution.

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization — teaser figure

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization

Yancheng Huang, Changsheng Wang, Chongyu Fan, Yicheng Lang, Bingqi Shang, Yang Zhang, Mingyi Hong, Qing Qu, Alvaro Velasquez, Sijia Liu

arXiv preprint 2026

Resolves objective-constraint interference in model steering by orthogonalizing the merged spectral subspace, then intervening only at the layers and steps that need it.

PaperCode
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning — teaser figure

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning

Bingqi Shang*, Yiwei Chen*, Yihua Zhang, Bingquan Shen, Sijia Liu

arXiv preprint 2025

Shows attention sinks act as gateways for backdooring LLM unlearning, so forgotten knowledge returns only when a hidden trigger is present.

HomepagePaperCode
Split Adaptation for Pre-trained Vision Transformers — teaser figure

Split Adaptation for Pre-trained Vision Transformers

Lixu Wang*, Bingqi Shang*, Yi Li, Payal Mohapatra, Wei Dong, Xiao Wang, Qi Zhu

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025

Splits a pre-trained ViT into quantized frontend and private backend so downstream adaptation protects both client data and model IP.

HomepagePaperCode