Wan: Open and Advanced Large-Scale Video Generative Models Paper • 2503.20314 • Published 8 days ago • 44
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy Paper • 2503.19757 • Published 9 days ago • 47
SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation Paper • 2503.09641 • Published 22 days ago • 30
FlowTok: Flowing Seamlessly Across Text and Image Tokens Paper • 2503.10772 • Published 21 days ago • 18
DAPO: An Open-Source LLM Reinforcement Learning System at Scale Paper • 2503.14476 • Published 16 days ago • 112
One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation Paper • 2503.13358 • Published 17 days ago • 90
Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation Paper • 2503.16430 • Published 14 days ago • 34
DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers Paper • 2503.14487 • Published 16 days ago • 27
Intuitive physics understanding emerges from self-supervised pretraining on natural videos Paper • 2502.11831 • Published Feb 17 • 18
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features Paper • 2502.04320 • Published Feb 6 • 36 • 3
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features Paper • 2502.04320 • Published Feb 6 • 36
BTS: Harmonizing Specialized Experts into a Generalist LLM Paper • 2502.00075 • Published Jan 31 • 1 • 1