From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks Paper • 2512.02580 • Published 10 days ago • 27
Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints Paper • 2510.08549 • Published Oct 9 • 6
Thought-Augmented Policy Optimization: Bridging External Guidance and Internal Capabilities Paper • 2505.15692 • Published May 21 • 14
DReSS: Data-driven Regularized Structured Streamlining for Large Language Models Paper • 2501.17905 • Published Jan 29 • 2
Boosting Multimodal Reasoning with MCTS-Automated Structured Thinking Paper • 2502.02339 • Published Feb 4 • 22
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking Paper • 2501.04519 • Published Jan 8 • 286
Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS Paper • 2411.18478 • Published Nov 27, 2024 • 37