ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
"LRM" 相关文章
Mitigating Overthinking through Reasoning Shaping
Mitigating Overthinking through Reasoning Shaping
2篇最新152页论文，RL+LLM被彻底讲透了！
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
From Noisy Traces to Stable Gradients: Bias-Variance Optimized Preference Optimization for Aligning Large Reasoning Models
CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
On The Fragility of Benchmark Contamination Detection in Reasoning Models
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
清华最新发布114页大型推理模型的强化学习综述
Correlation or Causation: Analyzing the Causal Structures of LLM and LRM Reasoning Process
Promoting Efficient Reasoning with Verifiable Stepwise Reward
Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization
ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
From Reasoning to Super-Intelligence: A Search-Theoretic Perspective
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
苹果拆解AI大脑，推理模型全是「装」的？Bengio兄弟合著
耗资1.3万，ASU团队揭秘o1推理王者！碾压所有LLM成本超高，关键还会PUA
