Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models Paper • 2503.20240 • Published 2 days ago • 21
Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy Paper • 2503.19757 • Published 3 days ago • 44
CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models Paper • 2503.18886 • Published 4 days ago • 17
Position: Interactive Generative Video as Next-Generation Game Engine Paper • 2503.17359 • Published 7 days ago • 57
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders Paper • 2503.18878 • Published 4 days ago • 104
Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation Paper • 2503.13070 • Published 11 days ago • 9
Concat-ID: Towards Universal Identity-Preserving Video Synthesis Paper • 2503.14151 • Published 10 days ago • 10
Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control Paper • 2503.14492 • Published 10 days ago • 16
EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer Paper • 2503.07027 • Published 18 days ago • 26