First Frame Is the Place to Go for Video Content Customization Paper • 2511.15700 • Published Nov 19, 2025 • 52
VisPlay: Self-Evolving Vision-Language Models from Images Paper • 2511.15661 • Published Nov 19, 2025 • 42
Self-Rewarding Vision-Language Model via Reasoning Decomposition Paper • 2508.19652 • Published Aug 27, 2025 • 84
Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation Paper • 2506.15068 • Published Jun 18, 2025 • 13