You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories Paper • 2605.21468 • Published 11 days ago • 49
Rethinking Cross-Layer Information Routing in Diffusion Transformers Paper • 2605.20708 • Published 11 days ago • 106
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment Paper • 2605.17602 • Published 11 days ago • 19
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published 18 days ago • 101