Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs Paper • 2510.13795 • Published Oct 15 • 56
Every Attention Matters: An Efficient Hybrid Architecture for Long-Context Reasoning Paper • 2510.19338 • Published Oct 22 • 114
Every Step Evolves: Scaling Reinforcement Learning for Trillion-Scale Thinking Model Paper • 2510.18855 • Published Oct 21 • 71
mvp-lab/LLaVA-OneVision-1.5-Mid-Training-85M Viewer • Updated 17 days ago • 91.5M • 214k • 48
LaSeR: Reinforcement Learning with Last-Token Self-Rewarding Paper • 2510.14943 • Published Oct 16 • 39
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling Paper • 2509.12201 • Published Sep 15 • 104