cs.AI（2025-06-24）
📊 共 7 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (4)
支柱二：RL算法与架构 (RL & Architecture) (2 🔗1)
支柱一：机器人控制 (Robot Control) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Persona-Assigned Large Language Models Exhibit Human-Like Motivated Reasoning | 研究表明人格分配的大型语言模型表现出人类般的动机推理 | large language model | ||
| 2 | Accurate and Energy Efficient: Local Retrieval-Augmented Generation Models Outperform Commercial Large Language Models in Medical Tasks | 提出可定制的RAG框架以提升医疗任务中的模型性能 | large language model | ||
| 3 | Adaptive Domain Modeling with Language Models: A Multi-Agent Approach to Task Planning | 提出TAPAS框架以解决复杂任务规划问题 | large language model | ||
| 4 | NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration | 提出NaviAgent以解决大规模工具导航中的规划与执行问题 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation | 提出Kling-Foley以解决视频与音频生成的同步问题 | flow matching multimodal | ||
| 6 | KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality | 提出KnowRL以解决慢思维模型的幻觉问题 | reinforcement learning large language model | ✅ |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | Is an object-centric representation beneficial for robotic manipulation ? | 提出对象中心表示以解决机器人操控中的多对象交互问题 | manipulation |