Learning from the Self-future: On-policy Self-distillation for dLLMs Paper • 2606.18195 • Published 2 days ago • 25
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space Paper • 2511.10555 • Published Nov 13, 2025 • 63
Sample By Step, Optimize By Chunk: Chunk-Level GRPO For Text-to-Image Generation Paper • 2510.21583 • Published Oct 24, 2025 • 31