cs.LG（2025-08-04）
📊 共 6 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)
支柱一：机器人控制 (Robot Control) (1)
支柱九：具身大模型 (Embodied Foundation Models) (1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Language Model Guided Reinforcement Learning in Quantitative Trading | 提出语言模型引导的强化学习以优化量化交易策略 | reinforcement learning large language model | ||
| 2 | MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs | 提出MolReasoner以解决分子推理不足问题 | reinforcement learning large language model chain-of-thought | ||
| 3 | CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment | 提出CAPO以解决LLM推理中的奖励分配问题 | reinforcement learning PPO large language model | ||
| 4 | CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search | 提出CRINN以解决近似最近邻搜索的优化问题 | reinforcement learning | ✅ |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Physics-Embedded Neural ODEs for Sim2Real Edge Digital Twins of Hybrid Power Electronics Systems | 提出物理嵌入神经ODE以解决混合动力电子系统的Sim2Real问题 | sim-to-real sim2real |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | LeanK: Learnable K Cache Channel Pruning for Efficient Decoding | 提出LeanK以解决大语言模型解码效率问题 | large language model |