Publications

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

Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space — teaser figure

Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space

Yiwei Chen*, Bingqi Shang*, Sijia Liu

COLM 2026

Traces LLM lineage from weight geometry alone, with no access to input data: spectral energy separates independently trained families and subspace alignment discriminates models built on a shared base, across more than 110 open-weight model pairs.

HomepageCode
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

COLM 2026

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

HomepagePaperCode
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

COLM 2026

Steers a model toward one objective without breaking a second: orthogonalizing the merged spectral subspace removes the interference between the two, and the intervention is applied only at the layers and steps that need it.

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

CVPR 2025

Splits a pre-trained vision transformer so the client runs a quantized frontend and the owner keeps a private backend, which protects the client data and the model weights at once rather than trading one for the other.

HomepagePaperCode