E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling Paper • 2412.14170 • Published Dec 18, 2024 • 2
VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate Paper • 2504.12259 • Published Apr 16
Cache-to-Cache: Direct Semantic Communication Between Large Language Models Paper • 2510.03215 • Published Oct 3 • 97
DiTFastAttn: Attention Compression for Diffusion Transformer Models Paper • 2406.08552 • Published Jun 12, 2024 • 25