3 papers
cs.CL2026
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
Yanke Zhou, Yiduo Li, Hanlin Tang +6
Long-context inference in large language models is bottlenecked by the quadratic cost of full attention. Existing efficient alternatives often rely either on native sparse training…
cs.LG2026
RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models
Xing Cong, Hanlin Tang, Kan Liu +4
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and disti…
cs.CV2026
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Haolun Zheng, Yu He, Tailun Chen +6
Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…