PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published Mar 26 • 53
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published Mar 24 • 91
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences Paper • 2601.07251 • Published Jan 12 • 11
TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows Paper • 2512.05150 • Published Dec 3, 2025 • 77
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning Paper • 2508.20751 • Published Aug 28, 2025 • 90