dOPSD: On-Policy Self-Distillation for Diffusion Language Models Paper • 2607.04428 • Published 4 days ago • 15
VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis Paper • 2605.22570 • Published May 21 • 24
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 431
Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information Paper • 2605.11609 • Published May 12 • 196