cs.AI(2025-03-27)

📊 共 23 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) (17 🔗3) 支柱二:RL算法与架构 (RL & Architecture) (6 🔗1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗
1 MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX MAVERIX:多模态视听评估与识别基准,用于评估LLM的视频理解能力 multimodal
2 Prompt, Divide, and Conquer: Bypassing Large Language Model Safety Filters via Segmented and Distributed Prompt Processing 提出一种分段分布式提示处理框架,绕过大型语言模型安全过滤器,生成恶意代码。 large language model
3 Research on the Design of a Short Video Recommendation System Based on Multimodal Information and Differential Privacy 提出基于多模态信息融合与差分隐私的短视频推荐系统,提升推荐效果并保护用户隐私 multimodal
4 Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap 提出LLM4TR框架,探索大语言模型在重塑交通系统中的多维角色 large language model
5 Using large language models to produce literature reviews: Usages and systematic biases of microphysics parametrizations in 2699 publications 利用大型语言模型分析气象文献:揭示微物理参数化方案的使用和偏差 large language model
6 Integrating Large Language Models For Monte Carlo Simulation of Chemical Reaction Networks 利用大语言模型进行化学反应网络的蒙特卡洛模拟 large language model
7 A Survey on (M)LLM-Based GUI Agents 综述:基于(M)LLM的GUI智能体,提升人机交互自动化水平 large language model multimodal
8 GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics GateLens:一种基于推理增强的大语言模型智能体,用于汽车软件发布分析 large language model chain-of-thought
9 GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise GenEdit:通过组合算子和持续改进解决企业级Text-to-SQL问题 large language model chain-of-thought
10 OntoAligner: A Comprehensive Modular and Robust Python Toolkit for Ontology Alignment OntoAligner:一个全面、模块化、鲁棒的本体对齐Python工具包 large language model
11 Intelligent IoT Attack Detection Design via ODLLM with Feature Ranking-based Knowledge Base 提出基于特征排序知识库的片上大语言模型(ODLLM)用于智能物联网攻击检测。 large language model
12 Immersive Multimedia Communication: State-of-the-Art on eXtended Reality Streaming 综述扩展现实流媒体技术,分析XR流量特征与用户体验优化方法。 multimodal
13 Data Poisoning in Deep Learning: A Survey 深度学习数据投毒攻击综述:全面分析与未来方向 large language model
14 debug-gym: A Text-Based Environment for Interactive Debugging 提出debug-gym:一个交互式调试的文本环境,用于提升LLM的代码能力 large language model
15 Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models 提出多图联合推理基准,评估并提升视觉-语言模型在复杂图结构数据上的理解能力。 instruction following
16 Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning 受神经可塑性启发,提出Drop In & Out学习策略,探索类脑AI新方向 large language model
17 Reinforced Model Merging 提出强化模型融合(RMM)框架,高效实现免训练的模型参数空间融合。 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🔗
18 LLM-Gomoku: A Large Language Model-Based System for Strategic Gomoku with Self-Play and Reinforcement Learning 提出基于LLM的五子棋AI系统,通过自博弈和强化学习提升策略能力 reinforcement learning large language model
19 UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning UI-R1:通过强化学习提升GUI智能体高效动作预测能力 reinforcement learning large language model multimodal
20 Knowledge Graphs as World Models for Semantic Material-Aware Obstacle Handling in Autonomous Vehicles 提出基于知识图谱的世界模型,提升自动驾驶车辆对语义材质的感知能力 world model embodied AI
21 Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning 提出神经符号模仿学习框架,用于学习机器人长时多步任务的技能抽象与规划。 imitation learning
22 From Deep Learning to LLMs: A survey of AI in Quantitative Investment 综述AI在量化投资中的应用:从深度学习到大语言模型 predictive model large language model
23 Alleviating LLM-based Generative Retrieval Hallucination in Alipay Search 提出一种缓解LLM生成式检索幻觉的框架,提升支付宝搜索质量。 distillation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页