Tag: Reinforcement Learning

All the articles with the tag "Reinforcement Learning".

• Purity Law for Generalizable Neural TSP Solvers

  Published: 15 May, 2025 |  at  11:09 AM

  

  98.11 🤔

  This paper introduces Purity Law (PuLa), a structural principle revealing sparsity bias in optimal TSP solutions, and proposes Purity Policy Optimization (PUPO), a training framework that significantly enhances the generalization of neural TSP solvers across diverse scales and distributions without inference overhead.

• Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning

  Published: 30 May, 2025 |  at  11:13 AM

  

  95.59 🤔

  本文通过仅使用920个蒸馏样本对Qwen2.5-32B基础模型进行监督微调，显著超越了资源密集的Zero-RL方法，并揭示了蒸馏模型通过拟人化语言和高级认知行为实现更灵活推理的机制。

• Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

  Published: 20 May, 2025 |  at  11:11 AM

  

  93.91 🤔

  本文通过 pass@k 指标系统评估 RLVR 在大型语言模型推理能力边界上的效果，发现 RLVR 仅提高采样效率而未引入新推理模式，其能力受限于基础模型，强调需改进 RL 范式以激发真正的新推理能力。

• Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning

  Published: 16 May, 2025 |  at  11:36 AM

  

  93.91 🤔

  Selftok introduces a non-spatial autoregressive visual tokenizer using diffusion timesteps, unifying vision-language models and enabling effective reinforcement learning for superior text-to-image generation, as demonstrated on GenEval and DPG-Bench benchmarks.

• Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs

  Published: 28 May, 2025 |  at  11:22 AM

  

  93.62 🤔

  本文提出 Universal Reasoner (UniR)，一种轻量级、可组合的推理模块，通过将预定义奖励转化为 token 级别指导信号，为冻结的大型语言模型提供高效的推理能力增强，并在数学推理与机器翻译任务上展现出优于部分基线的性能与跨模型迁移能力。