Han-Chen Zhang — accepted AI-conference papers

2026

DC-Merge: Improving Model Merging with Directional Consistency

Han-Chen Zhang, Zi-Hao Zhou, Mao-Lin Luo, Shimin Di, Min-Ling Zhang, Tong Wei

CVPR 2026

Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency of singular spaces between merged multi-task vector and ind

Cited by 0 Source ↗code ↗Scholar ↗

2026

Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation

Hao Gu, Mao-Lin Luo, Zi-Hao Zhou, Han-Chen Zhang, Min-Ling Zhang, Tong Wei

ICML 2026poster

Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most existing approaches treat continual learning as avoiding interference with past updates, rather than considering what properties make the current task-sp…

Cited by 0 Source ↗Scholar ↗