cs.AI（2025-01-28）

📊 共 12 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Search 提出MCTS-SQL框架，利用蒙特卡洛树搜索提升轻量级LLM在Text-to-SQL任务上的性能。 large language model
2 RadioLLM: Introducing Large Language Model into Cognitive Radio via Hybrid Prompt and Token Reprogrammings RadioLLM：通过混合提示和Token重编程将大型语言模型引入认知无线电 large language model
3 Fine-Tuning Open-Source Large Language Models to Improve Their Performance on Radiation Oncology Tasks: A Feasibility Study to Investigate Their Potential Clinical Applications in Radiation Oncology 通过微调开源大语言模型提升放射肿瘤任务性能，探索其临床应用潜力 large language model
4 SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model SafeRAG：构建RAG安全性评测基准，揭示其在对抗知识操纵攻击中的脆弱性 large language model ✅
5 Distilling Large Language Models for Network Active Queue Management 提出AQM-LLM，利用大语言模型提升网络主动队列管理性能 large language model
6 Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation 提出GAP框架，通过图结构优化对抗性提示生成，提升LLM内容审核能力 large language model multimodal ✅
7 From Natural Language to Extensive-Form Game Representations 提出一种基于LLM和上下文学习的框架，将自然语言博弈描述转换为扩展式博弈表示 large language model
8 Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical Solvers 提出语义自验证(SSV)方法，提升语言模型在逻辑推理任务中的准确性和可靠性。 large language model
9 Balancing Content Size in RAG-Text2SQL System 研究RAG-Text2SQL系统中检索文档大小与质量的平衡策略，提升查询准确性。 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🔗⭐
10 SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training 比较SFT与RL在基础模型后训练中的作用 reinforcement learning foundation model
11 Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decoding 提出基于群体智慧解码（WOC）的大语言模型（LLM）估算方法，提升世界知识利用率。 world model large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
12 Integrating Reinforcement Learning and AI Agents for Adaptive Robotic Interaction and Assistance in Dementia Care 提出结合强化学习与AI代理的自适应机器人交互系统，用于痴呆症护理。 humanoid humanoid robot reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页