9 papers
Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
Yancheng Huang, Changsheng Wang, Chongyu Fan +7
Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, an…
Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
Justin Lee, Zheda Mai, Jinsu Yoo +3
Machine unlearning--the ability to remove designated concepts from a pre-trained model--has advanced rapidly, particularly for text-to-image diffusion models. However, existing met…
LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
Chongyu Fan, Changsheng Wang, Yancheng Huang +2
Machine unlearning for large language models (LLMs) aims to remove undesired data, knowledge, and behaviors (e.g., for safety, privacy, or copyright) while preserving useful model…
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Yicheng Lang, Yihua Zhang, Chongyu Fan +3
Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks.…
EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
Jinghan Jia, Hadi Reisizadeh, Chongyu Fan +3
Large language models (LLMs) have shown remarkable reasoning capabilities when trained with chain-of-thought (CoT) supervision. However, the long and verbose CoT traces, especially…
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
Changsheng Wang, Chongyu Fan, Yihua Zhang +5
Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities…