Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds Paper • 2610.28698 • Published 10 days ago • 86
TPPO: Tracking-Value PPO For Language Model Reasoning Paper • 2610.16794 • Published 18 days ago • 95
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning Paper • 2608.14277 • Published Aug 14 • 36