AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper ⢠2605.13724 ⢠Published 2 days ago ⢠79
HumanNet: Scaling Human-centric Video Learning to One Million Hours Paper ⢠2605.06747 ⢠Published 8 days ago ⢠50
deepseek-ai/DeepSeek-V4-Flash Text Generation ⢠158B ⢠Updated 9 days ago ⢠1.53M ⢠⢠1.08k
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper ⢠2601.07832 ⢠Published Jan 12 ⢠53