INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats Paper • 2510.25602 • Published Oct 29 • 76
PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models Paper • 2506.16054 • Published Jun 19 • 60
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation Paper • 2506.19852 • Published Jun 24 • 41