arXiv cs.AI / cs.LG / cs.CL·9d agoVideo DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation#diffusion-transformer#hybrid-attention#inference-efficiencyAI research
Hugging Face daily papers·10d agoVideo DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation#diffusion-transformer#distillation#inference-efficiency
Hugging Face daily papers·13d agoLynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows#agentic-workflows#diffusion-transformer#multimodal1
Hugging Face daily papers·16d agoStepAudio 3 Music Technical Report#diffusion-transformer#dpo#flow-matching
arXiv cs.AI / cs.LG / cs.CL·22d agoUniMate: One Unified Model to Animate Diverse Skeletons#3d-animation#diffusion-transformer#foundation-modelAI research
Hugging Face daily papers·23d agoUniMate: One Unified Model to Animate Diverse Skeletons#3d-animation#dataset#diffusion-transformer