Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published Nov 9, 2025 • 142
Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models Paper • 2509.26628 • Published Sep 30, 2025 • 17 • 3