CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation Paper • 2605.25378 • Published 6 days ago • 50
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 18 days ago • 101
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Paper • 2604.24763 • Published Apr 27 • 71
Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Paper • 2602.06422 • Published Feb 6 • 47
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer Paper • 2511.22699 • Published Nov 27, 2025 • 246
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length Paper • 2512.04677 • Published Dec 4, 2025 • 178