The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published 3 days ago • 90
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG Paper • 2603.23497 • Published 22 days ago • 91
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference Paper • 2603.25730 • Published 20 days ago • 52
World Craft: Agentic Framework to Create Visualizable Worlds via Text Paper • 2601.09150 • Published Jan 14 • 19
MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences Paper • 2601.07251 • Published Jan 12 • 11
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking Paper • 2601.06487 • Published Jan 10 • 54
Yume-1.5: A Text-Controlled Interactive World Generation Model Paper • 2512.22096 • Published Dec 26, 2025 • 61