2 papers
cs.CV2026
Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining
Chongxin Li, Hanzhang Wang, Lian Duan
Safety prompts constitute an interpretable layer of defense against jailbreak attacks in vision-language models (VLMs); however, their efficacy is constrained by the models' latent…
cs.DC2025
Static Batching of Irregular Workloads on GPUs: Framework and Application to Efficient MoE Model Inference
Yinghan Li, Yifei Li, Jiejing Zhang +13
It has long been a problem to arrange and execute irregular workloads on massively parallel devices. We propose a general framework for statically batching irregular workloads into…