PAPER·2 days agoSol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention SparsificationHugging Face Papers
PAPER·2 days agoMemory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion TransformersApple Machine Learning Research
PAPER·5 days agoStreaming Multi-Agent Autoregressive Diffusion Model with World State RegistersHugging Face Papers
PAPER·July 23, 2026Spectral Transformation for Layer-wise Global Rank Discovery in Federated LoRA for Vision TransformersarXiv
PAPER·July 20, 2026RayRoPE: Projective Ray Positional Encoding for Multi-View AttentionApple Machine Learning Research
PAPER·June 2, 2026Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative DecodingHugging Face Papers
