cs.AI（2025-08-07）

📊 共 38 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (26 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗3) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (26 篇)

#题目一句话要点标签🔗⭐
1 JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering 提出JPS以解决多模态大语言模型的越狱攻击问题 large language model multimodal ✅
2 MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models 提出MedMKEB：用于评估医学多模态大语言模型知识编辑的综合基准 large language model multimodal
3 MV-Debate: Multi-view Agent Debate with Dynamic Reflection Gating for Multimodal Harmful Content Detection in Social Media 提出MV-Debate多视角Agent辩论框架，用于社交媒体中多模态有害内容检测。 multimodal
4 Can Large Language Models Generate Effective Datasets for Emotion Recognition in Conversations? 利用小型语言模型生成对话情绪识别数据集，提升模型泛化能力 large language model
5 Large Language Models Transform Organic Synthesis From Reaction Prediction to Automation 大型语言模型将有机合成从反应预测转变为自动化 large language model
6 StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models StructVRM：通过结构化可验证奖励模型对齐多模态推理 multimodal
7 Driver Assistant: Persuading Drivers to Adjust Secondary Tasks Using Large Language Models 利用大语言模型辅助驾驶员调整次要任务，提升道路安全性 large language model
8 Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination 提出一种轻量级、低幻觉的大语言模型事件响应规划方法 large language model
9 Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models 提出Tool Graph Retriever(TGR)，利用工具依赖图提升大语言模型工具检索性能 large language model
10 LLM-BI: Towards Fully Automated Bayesian Inference with Large Language Models 提出LLM-BI，利用大语言模型实现全自动贝叶斯推断 large language model
11 Safety of Embodied Navigation: A Survey 具身导航安全性综述：分析攻击、防御与评估方法，展望未来研究方向 embodied AI large language model
12 QA-Dragon: Query-Aware Dynamic RAG System for Knowledge-Intensive Visual Question Answering 提出QA-Dragon，用于知识密集型视觉问答的查询感知动态RAG系统 large language model multimodal
13 A Framework for Inherently Safer AGI through Language-Mediated Active Inference 提出一种基于语言介导主动推理的AGI安全框架，旨在实现内生安全性。 large language model
14 LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering 利用LLM智能体进行音乐推荐，效果优于传统内容过滤方法 large language model
15 Streamlining Admission with LOR Insights: AI-Based Leadership Assessment in Online Master's Program 提出LORI：利用AI评估推荐信中的领导力，优化在线硕士项目招生流程。 large language model
16 AI-Guided Exploration of Large-Scale Codebases 提出一种AI引导的代码探索方法，结合逆向工程与LLM以提升代码理解效率。 large language model
17 KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation 发布KuaiLive：一个用于直播推荐的实时交互数据集 TAMP ✅
18 Simulating Human-Like Learning Dynamics with LLM-Empowered Agents 提出LearnerAgent，利用LLM模拟人类学习动态，揭示LLM的认知局限性。 large language model
19 CLAPP: The CLASS LLM Agent for Pair Programming CLAPP：用于配对编程的CLASS LLM智能体，提升科研效率 large language model
20 Auto-Eval Judge: Towards a General Agentic Framework for Task Completion Evaluation 提出Auto-Eval Judge通用框架，用于评估Agent任务完成质量，提升评估与人类对齐度。 foundation model
21 Multi-Modal Multi-Behavior Sequential Recommendation with Conditional Diffusion-Based Feature Denoising 提出M$^3$BSR模型，利用条件扩散去噪提升多模态多行为序列推荐精度 multimodal
22 NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making NomicLaw：利用LLM进行协同法律制定，探索涌现信任与策略性论证 large language model
23 The Term 'Agent' Has Been Diluted Beyond Utility and Requires Redefinition 重新定义“Agent”概念，解决AI领域术语歧义问题，提升研究清晰度和可复现性 large language model
24 EvoGraph: Hybrid Directed Graph Evolution toward Software 3.0 EvoGraph：混合有向图进化框架，迈向软件3.0时代 large language model
25 Situated Epistemic Infrastructures: A Diagnostic Framework for Post-Coherence Knowledge 提出情境化认知基础设施框架，诊断后连贯性时代混合人机系统的知识权威性问题。 large language model
26 Grid-Agent: An LLM-Powered Multi-Agent System for Power Grid Control Grid-Agent：基于LLM的多智能体系统，用于电力网络控制与故障恢复。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
27 IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model 提出IRL-VLA，通过逆强化学习奖励世界模型训练视觉-语言-动作策略，提升端到端自动驾驶性能。 reinforcement learning PPO imitation learning
28 HiSTM: Hierarchical Spatiotemporal Mamba for Cellular Traffic Forecasting HiSTM：用于蜂窝网络流量预测的分层时空Mamba模型 Mamba MAE spatiotemporal
29 Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation 提出基于强化学习偏好优化的框架，解决歌词到歌曲生成中的内容幻觉问题 reinforcement learning PPO DPO
30 InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization InfiGUI-G1提出自适应探索策略优化AEPO，提升GUI界面操作的语义对齐能力 reinforcement learning large language model multimodal ✅
31 Klear-CodeTest: Scalable Test Case Generation for Code Reinforcement Learning Klear-CodeTest：用于代码强化学习的可扩展测试用例生成框架 reinforcement learning large language model ✅
32 EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search EasySize：基于LLM引导的启发式搜索实现弹性模拟电路尺寸设计 reinforcement learning AMP large language model
33 Quantum-Efficient Reinforcement Learning Solutions for Last-Mile On-Demand Delivery 提出基于量子增强强化学习的末端按需配送方案，优化大规模车辆路径问题 reinforcement learning PPO
34 The Missing Reward: Active Inference in the Era of Experience 利用主动推理弥合具身智能鸿沟，实现无需人工奖励的自主学习 world model reward design large language model
35 InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities InfiAlign：一种可扩展且高效的LLM对齐框架，提升推理能力 DPO direct preference optimization large language model ✅
36 Posterior-GRPO: Rewarding Reasoning Processes in Code Generation 提出Posterior-GRPO，通过奖励代码生成中的推理过程提升模型性能。 reinforcement learning large language model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
37 Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses 利用大语言模型进行空间数据集成，解决传统方法的局限性。 spatial relationship large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
38 Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translation 综述性论文：生成式AI在医学影像中的应用、进展与临床转化 spatiotemporal foundation model multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页