2 papers
cs.LG2026
MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention
Jianlin Yu, Jing Lin, Linghui Kong +13
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct M…
cs.CV2026
RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation
Yaofu Liu, Wanli Lan, Jinxi Li +2
In , the attention mechanism remains a primary computational bottleneck due to its…