3 papers
cs.LG2026
Thin Keys, Full Values: Reducing KV Cache via Low-Dimensional Attention Selection
Hengshuai Yao, Xing Chen, Ahmed Murtadha +1
Standard Transformer attention uses identical dimensionality for queries, keys, and values, yet these components serve different roles: queries and keys produce scalar attention we…
cs.DC2025
DIP: Efficient Large Multimodal Model Training with Dynamic Interleaved Pipeline
Zhenliang Xue, Hanpeng Hu, Xing Chen +7
Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible c…
cs.DC2025
DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training
Xin Tan, Yuetao Chen, Yimin Jiang +6
Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in sc…