Towards Flash Thinking via Decoupled Advantage Policy Optimization Paper • 2510.15374 • Published Oct 17, 2025 • 2
ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning Paper • 2512.13095 • Published Dec 15, 2025 • 3
RAVE: Re-Allocating Visual Attention in Large Multimodal Models Paper • 2605.18359 • Published May 26 • 2
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective Paper • 2605.12969 • Published May 30 • 3
P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document Parsing Paper • 2610.21979 • Published Oct 15 • 7
SkillDuet: Co-Evolving Models and Skills through Response Feedback Paper • 2611.12109 • Published 7 days ago • 9