cs.LG（2025-08-24）
📊 共 2 篇论文
🎯 兴趣领域导航
🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling | 提出TreePO以解决强化学习推理效率与效果之间的矛盾 | reinforcement learning large language model |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 2 | LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components | 通过情感与逻辑成分分解LLM自信度以应对过度自信问题 | large language model |