cs.AI（2025-02-07）

📊 共 16 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) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗⭐
1 MedMimic: Physician-Inspired Multimodal Fusion for Early Diagnosis of Fever of Unknown Origin MedMimic：一种受医生诊断启发的多模态融合框架，用于不明原因发热的早期诊断 multimodal
2 Dynamic Chain-of-Thought: Towards Adaptive Deep Reasoning 提出动态思维链（D-CoT），自适应调整推理时间和步骤，降低计算资源消耗。 chain-of-thought
3 Enhancing Phishing Email Identification with Large Language Models 利用大型语言模型增强钓鱼邮件识别能力 large language model
4 Every Software as an Agent: Blueprint and Case Study 提出一种赋予LLM软件内部访问权限的Agent框架，提升软件智能水平。 large language model multimodal
5 Detection of LLM-Generated Java Code Using Discretized Nested Bigrams 提出离散化嵌套Bigram频率特征，用于检测LLM生成的Java代码 large language model
6 Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search 量化分析并缓解AI网页搜索中基于LLM的不安全风险 large language model
7 Oracular Programming: A Modular Foundation for Building LLM-Enabled Software 提出Oracular Programming，用于构建可模块化、可控的LLM驱动软件 large language model
8 Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Tools Agentic Reasoning：利用Agent工具增强LLM推理能力的新框架 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
9 Generating Symbolic World Models via Test-time Scaling of Large Language Models 通过大语言模型测试时缩放生成符号世界模型，解决复杂规划问题。 world model large language model
10 Adaptive Graph of Thoughts: Test-Time Adaptive Reasoning Unifying Chain, Tree, and Graph Structures 提出自适应思维图以解决大语言模型推理效率问题 reinforcement learning large language model chain-of-thought
11 A New Paradigm in Tuning Learned Indexes: A Reinforcement Learning Enhanced Approach LITune：强化学习驱动的自适应学习索引结构调优框架 reinforcement learning deep reinforcement learning DRL
12 Redistributing Rewards Across Time and Agents for Multi-Agent Reinforcement Learning 提出TAR²以解决多智能体强化学习中的奖励分配问题 reinforcement learning reward shaping
13 Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization 提出LSPO框架，解决狼人杀游戏中LLM智能体的策略学习与语言交互难题 DPO direct preference optimization large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
14 Probabilistic Artificial Intelligence 探讨概率人工智能：关注不确定性建模与序贯决策 quadruped locomotion reinforcement learning
15 Bridging the Gap in XAI-Why Reliable Metrics Matter for Explainability and Compliance 提出基于标准化指标的AI治理框架，提升可解释性和合规性 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
16 Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance Koel-TTS：通过偏好对齐和无分类器指导增强基于LLM的语音生成 classifier-free guidance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页