3 papers
cs.CR2026
CircuitBreak: Pruning a Sparse Safety Circuit of Neurons
Jincheng Ying, Li Wenlin, Wencheng Yang +1
White-box neuron pruning has shown that refusal in large language models (LLMs) can depend on a small, removable set of feed-forward (FFN) channels. Existing attacks either need ca…
cs.CV2026
Bridging Diffusion Pruning and Step Distillation with Teacher-Aligned Repair
Jincheng Ying, Li Wenlin, Minghui Xu +1
Diffusion models generate high-quality images, but their inference cost comes from two sources: large denoising networks and repeated denoising steps. Existing compression pipeline…
cs.CV2026
Efficient Diffusion Distillation via Embedding Loss
Jincheng Ying, Yitao Chen, Li Wenlin +2
Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computatio…