cs.AI(2025-07-07)

📊 共 33 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九:具身大模型 (Embodied Foundation Models) (22 🔗1) 支柱二:RL算法与架构 (RL & Architecture) (7 🔗2) 支柱一:机器人控制 (Robot Control) (2) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱九:具身大模型 (Embodied Foundation Models) (22 篇)

#题目一句话要点标签🔗
1 LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants LEGO Co-builder:探索细粒度视觉语言建模,用于多模态乐高组装助手 multimodal instruction following
2 Advancing Financial Engineering with Foundation Models: Progress, Applications, and Challenges 综述金融领域专用大模型:进展、应用与挑战 foundation model multimodal
3 Activation Steering for Chain-of-Thought Compression 提出激活引导压缩(ASC),通过注入引导向量压缩CoT推理链,提升LLM推理效率。 large language model chain-of-thought
4 EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation EXPOTION:提出一种利用面部表情和肢体动作控制的多模态音乐生成模型。 multimodal
5 Architecting Clinical Collaboration: Multi-Agent Reasoning Systems for Multimodal Medical VQA 构建临床协作:用于多模态医学VQA的多智能体推理系统 multimodal
6 When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors CoT监控在必要时能有效防止语言模型逃避监控,但需持续压力测试。 chain-of-thought
7 OASBuilder: Generating OpenAPI Specifications from Online API Documentation with Large Language Models OASBuilder:利用大语言模型从在线API文档生成OpenAPI规范 large language model
8 Application and Evaluation of Large Language Models for Forecasting the Impact of Traffic Incidents 利用大语言模型预测交通事故对交通流的影响 large language model
9 Large Language Models for Network Intrusion Detection Systems: Foundations, Implementations, and Future Directions 探索LLM在网络入侵检测系统中的应用,构建认知型安全防御体系 large language model
10 Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message 提出特洛伊木马提示,通过伪造助手消息破解对话多模态模型 multimodal
11 A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models 提出QMKGF,通过查询感知的多路径知识图谱融合增强大语言模型的检索增强生成效果。 large language model
12 MedGemma Technical Report MedGemma:基于Gemma的医学视觉-语言基础模型,提升医疗AI任务性能。 foundation model multimodal
13 LVM4CSI: Enabling Direct Application of Pre-Trained Large Vision Models for Wireless Channel Tasks LVM4CSI:利用预训练大视觉模型解决无线信道任务 large language model
14 Conversational Education at Scale: A Multi-LLM Agent Workflow for Procedural Learning and Pedagogic Quality Assessment 提出WikiHowAgent,利用多LLM智能体工作流实现可扩展的对话式程序学习与教学质量评估。 large language model
15 Deep Research Comparator: A Platform For Fine-grained Human Annotations of Deep Research Agents 提出Deep Research Comparator平台,用于深度研究Agent的细粒度人工标注与评估。 large language model
16 CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale CREW-WILDFIRE:大规模Agentic多智能体协作基准测试环境 large language model
17 Assessing the Ecological Impact of AI 倡导AI生态影响评估,关注生成式AI可持续性分析 large language model
18 MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction 提出MARBLE多智能体规则推理引擎,解决事故严重程度预测难题。 chain-of-thought
19 ASSURE: Metamorphic Testing for AI-powered Browser Extensions ASSURE:针对AI浏览器扩展的变质测试框架,提升测试效率并发现安全漏洞。 large language model
20 Narrowing the Gap: Supervised Fine-Tuning of Open-Source LLMs as a Viable Alternative to Proprietary Models for Pedagogical Tools 通过监督微调开源LLM,为教学工具提供媲美专有模型的替代方案 large language model
21 Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems 提出AgentXposed框架,用于检测LLM多智能体系统中隐藏意图的恶意智能体。 large language model
22 Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World 音频对抗噪声可操控现实世界中的音频大语言模型 large language model

🔬 支柱二:RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗
23 DARIL: When Imitation Learning outperforms Reinforcement Learning in Surgical Action Planning DARIL在手术动作规划中超越强化学习,解决实时辅助难题 reinforcement learning imitation learning world model
24 SPATIA: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes SPATIA:用于预测和生成空间细胞表型的多模态模型 predictive model multimodal
25 ChipSeek-R1: Generating Human-Surpassing RTL with LLM via Hierarchical Reward-Driven Reinforcement Learning ChipSeek-R1:通过层级奖励驱动强化学习,利用LLM生成超越人类水平的RTL代码 reinforcement learning large language model
26 AI Mother Tongue: Self-Emergent Communication in MARL via Endogenous Symbol Systems 提出基于内生符号系统的AI母语框架,解决MARL中的涌现通信难题。 reinforcement learning VQ-VAE large language model
27 Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models? 提出MoPPS,在线预测Prompt难度,加速推理模型RL微调。 reinforcement learning large language model
28 Inaugural MOASEI Competition at AAMAS'2025: A Technical Report MOASEI竞赛提出开放Agent系统评估基准,聚焦动态环境下的决策。 predictive model large language model
29 Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation HIPHOP:结合LLM语义与层级意图引导的会话推荐模型 contrastive learning large language model

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
30 The Hidden Threat in Plain Text: Attacking RAG Data Loaders 揭示RAG数据加载环节的隐蔽威胁:针对文档注入的知识投毒攻击 manipulation large language model
31 Q-Detection: A Quantum-Classical Hybrid Poisoning Attack Detection Method 提出Q-Detection:一种量子-经典混合的数据投毒攻击检测方法 manipulation

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

#题目一句话要点标签🔗
32 Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving 提出解耦推理与证明框架,显著提升LLM在IMO难题上的求解能力 IMoS large language model

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

#题目一句话要点标签🔗
33 Leadership Detection via Time-Lagged Correlation-Based Network Inference 提出基于时滞相关性的网络推断方法,用于解决群体行为中的领导者检测问题。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页