Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification Paper • 2607.24027 • Published 10 days ago • 36
MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model Paper • 2606.17800 • Published Jun 16 • 13
Optimizing Few-Step Generation with Adaptive Matching Distillation Paper • 2602.07345 • Published Feb 7 • 9
PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers Paper • 2602.01077 • Published Feb 1 • 4
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models Paper • 2503.16257 • Published Mar 20, 2025 • 28
Autoregressive Image Generation with Randomized Parallel Decoding Paper • 2503.10568 • Published Mar 13, 2025 • 9