Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers
Bingxin Xing, Yu Zhang, Jiatong Ding +2
Diffusion Transformers (DiTs) have become a common backbone for high-quality text-to-image and text-to-video generation, but repeated dense self-attention remains a major inference…
cs.AI2026
HyQuant: Hybrid-Precision Quantization for LLM Attention
Jiatong Ding, Bingxin Xing, Yu Zhang +9
Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module often introdu…
cond-mat.mtrl-sci2026
Fragmenting Diffusion Pathways Confers Extraordinary Radiation Resistance in Refractory Multicomponent Alloys
Bin Xing, Bijun Xie, Wanjuan Zou +11
The accumulation and growth of vacancy clusters under irradiation is a pivotal degradation mode for structural materials in extreme environments. Even tungsten undergoes rapid defe…