cs.AI（2025-07-27）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱一：机器人控制 (Robot Control) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Lessons from A Large Language Model-based Outdoor Trail Recommendation Chatbot with Retrieval Augmented Generation 提出基于大语言模型与检索增强生成（RAG）的户外步道推荐聊天机器人Judy large language model
2 A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature 提出基于多模态大语言模型的多智能体系统，用于化学文献信息抽取。 large language model multimodal
3 MazeEval: A Benchmark for Testing Sequential Decision-Making in Language Models 提出MazeEval基准以评估语言模型的空间推理能力 embodied AI large language model
4 The Blessing and Curse of Dimensionality in Safety Alignment 揭示大语言模型高维表示的双刃剑效应：安全对齐的维度诅咒与祝福 large language model
5 When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions 评估代码生成模型对模糊、矛盾和不完整任务描述的鲁棒性 large language model
6 AI Should Be More Human, Not More Complex 研究表明AI搜索应更注重简洁和可信度，而非过度复杂的表达 large language model
7 Artificial Intelligence In Patent And Market Intelligence: A New Paradigm For Technology Scouting 提出一种基于LLM的AI平台，用于加速工业研发中的技术 scouting 和解决方案发现。 large language model
8 SDD: Self-Degraded Defense against Malicious Fine-tuning 提出自降解防御SDD，抵抗恶意微调对开源大语言模型的安全攻击 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
9 The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models 提出奖励-策略映射理论框架，分析大语言模型策略脆性和不稳定性问题 reinforcement learning RLHF large language model
10 NeuroCLIP: A Multimodal Contrastive Learning Method for rTMS-treated Methamphetamine Addiction Analysis NeuroCLIP：一种用于rTMS治疗的甲基苯丙胺成瘾分析的多模态对比学习方法 contrastive learning multimodal
11 Learning to Align Human Code Preferences 提出自适应偏好优化APO，动态对齐LLM的代码偏好，提升代码生成质量。 DPO direct preference optimization large language model
12 Multi-Agent Reinforcement Learning for Dynamic Mobility Resource Allocation with Hierarchical Adaptive Grouping 提出基于分层自适应分组的多智能体强化学习方法，用于动态交通资源分配。 reinforcement learning
13 StepFun-Prover Preview: Let's Think and Verify Step by Step StepFun-Prover Preview：提出工具集成推理的大语言模型，用于形式化定理证明。 reinforcement learning large language model
14 Concept Learning for Cooperative Multi-Agent Reinforcement Learning 提出基于概念瓶颈的多智能体强化学习方法CMQ，提升合作策略的可解释性与性能。 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
15 VLMPlanner: Integrating Visual Language Models with Motion Planning VLMPlanner：融合视觉语言模型与运动规划，提升复杂场景自动驾驶性能 motion planning large language model

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
16 Improving Subgraph Matching by Combining Algorithms and Graph Neural Networks 提出HFrame框架，结合传统算法与图神经网络提升子图同态匹配效率 OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页