cs.AI（2025-01-03）

📊 共 16 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring METAGENE-1：用于疫情监测的宏基因组基础模型 foundation model
2 Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap 提出冷启动推荐方法以应对大语言模型时代的挑战 large language model ✅
3 BERT4MIMO: A Foundation Model using BERT Architecture for Massive MIMO Channel State Information Prediction 提出BERT4MIMO，利用BERT架构预测大规模MIMO信道状态信息 foundation model
4 How Toxic Can You Get? Search-based Toxicity Testing for Large Language Models EvoTox：一种基于搜索的大语言模型毒性测试框架，有效评估对齐后模型的潜在毒性。 large language model
5 Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition 提出AVGER以解决音视频语音识别中的生成错误校正问题 large language model multimodal ✅
6 AgentRefine: Enhancing Agent Generalization through Refinement Tuning AgentRefine：通过精炼调优增强LLM Agent的泛化能力 large language model
7 Effective LLM-Driven Code Generation with Pythoness Pythoness：利用领域特定语言提升LLM驱动的代码生成质量 large language model
8 A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses 提出MACO多智能体对话Bandit模型，用于在线评估和选择用户对齐的LLM响应 large language model
9 LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries 利用LLM分析法律援助用户查询：理解用户法律需求 large language model
10 BARTPredict: Empowering IoT Security with LLM-Driven Cyber Threat Prediction BARTPredict：利用LLM驱动的网络威胁预测增强物联网安全 large language model
11 PersonaAI: Leveraging Retrieval-Augmented Generation and Personalized Context for AI-Driven Digital Avatars PersonaAI：利用RAG和个性化上下文的AI数字形象 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
12 BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems 提出BLAST：一种针对合作多智能体深度强化学习系统的隐蔽后门杠杆攻击 reinforcement learning deep reinforcement learning spatiotemporal
13 Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models Auto-RT：一种自动化的LLM红队测试框架，用于探索和优化对抗攻击策略。 reinforcement learning large language model
14 SDPO: Segment-Level Direct Preference Optimization for Social Agents 提出SDPO：用于社交智能体的段落级直接偏好优化方法 DPO direct preference optimization large language model ✅
15 Contrastive Learning Augmented Social Recommendations 提出对比学习增强的社交推荐模型CLSRec，解决冷启动用户推荐问题。 contrastive learning distillation ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning 提出分层目标条件策略规划，解决人形机器人多目标强化学习稀疏奖励问题 humanoid humanoid robot reinforcement learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页