cs.AI（2025-08-05）

📊 共 44 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) (28 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (12) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (28 篇)

#题目一句话要点标签🔗⭐
1 CogBench: A Large Language Model Benchmark for Multilingual Speech-Based Cognitive Impairment Assessment 提出CogBench以解决多语言认知障碍评估的通用性问题 large language model multimodal chain-of-thought
2 Error Detection and Correction for Interpretable Mathematics in Large Language Models 提出EDCIM以解决大型语言模型数学推理中的错误检测与修正问题 large language model chain-of-thought
3 Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions 提出Geoint-R1以解决多模态几何推理问题 large language model multimodal
4 Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series? 提出SymbolBench基准以评估时间序列的符号推理能力 large language model
5 Semantic-aware Graph-guided Behavior Sequences Generation with Large Language Models for Smart Homes 提出SmartGen以解决智能家居行为数据生成问题 large language model ✅
6 Multi-Objective Infeasibility Diagnosis for Routing Problems Using Large Language Models 提出多目标不可行性诊断方法以解决路由问题 large language model
7 Can Large Language Models Bridge the Gap in Environmental Knowledge? 利用大型语言模型提升大学生环境知识教育的有效性 large language model
8 ToolVQA: A Dataset for Multi-step Reasoning VQA with External Tools 提出ToolVQA以解决多步骤推理VQA中的工具使用能力不足问题 foundation model multimodal
9 A Comparative Study of Neurosymbolic AI Approaches to Interpretable Logical Reasoning 比较神经符号AI方法以提升逻辑推理能力 large language model
10 MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework 提出MOTIF框架以解决NP难度组合优化问题 large language model
11 Topos Theory for Generative AI and LLMs 基于拓扑理论设计新型生成AI架构以提升LLM性能 large language model
12 Automated Algorithmic Discovery for Scientific Computing through LLM-Guided Evolutionary Search: A Case Study in Gravitational-Wave Detection 提出Evo-MCTS框架以解决科学计算中的算法自动发现问题 large language model
13 Probing the Gaps in ChatGPT Live Video Chat for Real-World Assistance for People who are Blind or Visually Impaired 探讨ChatGPT实时视频聊天在盲人辅助中的应用与挑战 multimodal
14 Refining Critical Thinking in LLM Code Generation: A Faulty Premise-based Evaluation Framework 提出FPBench框架以解决LLM代码生成中的错误前提问题 large language model
15 Block: Balancing Load in LLM Serving with Context, Knowledge and Predictive Scheduling 提出Block框架以优化大语言模型服务中的负载均衡问题 large language model
16 Data Dependency-Aware Code Generation from Enhanced UML Sequence Diagrams 提出UML2Dep框架以解决服务导向架构中的数据依赖问题 large language model
17 Wearable Music2Emotion : Assessing Emotions Induced by AI-Generated Music through Portable EEG-fNIRS Fusion 提出MEEtBrain以解决音乐情感分析中的多重限制问题 multimodal ✅
18 Agoran: An Agentic Open Marketplace for 6G RAN Automation 提出Agoran以解决6G RAN自动化中的利益相关者协调问题 large language model
19 From Legacy to Standard: LLM-Assisted Transformation of Cybersecurity Playbooks into CACAO Format 提出基于大语言模型的自动化网络安全剧本转化方法 large language model
20 Nemori: Self-Organizing Agent Memory Inspired by Cognitive Science 提出Nemori以解决长时记忆不足问题 large language model
21 Industrial LLM-based Code Optimization under Regulation: A Mixture-of-Agents Approach 提出混合代理方法以解决受监管环境下的代码优化问题 large language model
22 Artificial Intelligence and Generative Models for Materials Discovery -- A Review 综述人工智能与生成模型在材料发现中的应用与挑战 multimodal
23 Principle-Guided Verilog Optimization: IP-Safe Knowledge Transfer via Local-Cloud Collaboration 提出IP保护的Verilog优化框架以解决硬件设计安全问题 large language model
24 Trustworthiness of Legal Considerations for the Use of LLMs in Education 提出合规中心的AI治理框架以应对教育领域LLMs的法律挑战 large language model
25 Who is a Better Player: LLM against LLM 提出对抗性基准框架以评估大型语言模型的表现 large language model
26 Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation 提出可验证合成数据生成框架以训练可信优化建模代理 large language model
27 VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs 提出VFLAIR-LLM以解决数据隐私与资源限制下的LLM适应问题 large language model ✅
28 Unified Tool Integration for LLMs: A Protocol-Agnostic Approach to Function Calling 提出统一工具集成方法以解决LLMs工具生态碎片化问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗⭐
29 ClinicalFMamba: Advancing Clinical Assessment using Mamba-based Multimodal Neuroimaging Fusion 提出ClinicalFMamba以解决多模态医学图像融合问题 Mamba SSM state space model
30 Compressing Chain-of-Thought in LLMs via Step Entropy 提出基于步骤熵的链式思维压缩方法以提高LLM推理效率 reinforcement learning large language model chain-of-thought
31 Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety 提出Evo-MARL以解决多智能体系统安全性问题 reinforcement learning large language model multimodal
32 Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play 提出Game Reasoning Arena框架以评估大型语言模型的推理能力 reinforcement learning large language model
33 Agent Lightning: Train ANY AI Agents with Reinforcement Learning 提出Agent Lightning框架以实现灵活的强化学习训练 reinforcement learning large language model
34 When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs 提出WhisperInject框架以破解音频语言模型的安全性 reinforcement learning large language model multimodal
35 Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning 提出BPO框架以解决稀疏奖励长时间规划问题 reinforcement learning curriculum learning chain-of-thought
36 Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback 提出DLPO框架以提升TTS扩散模型的实时性能 reinforcement learning RLHF
37 BitsAI-Fix: LLM-Driven Approach for Automated Lint Error Resolution in Practice 提出BitsAI-Fix以解决企业代码中的自动化Lint错误修复问题 reinforcement learning large language model
38 Probing and Enhancing the Robustness of GNN-based QEC Decoders with Reinforcement Learning 提出基于强化学习的框架以增强GNN量子纠错解码器的鲁棒性 reinforcement learning
39 Do GNN-based QEC Decoders Require Classical Knowledge? Evaluating the Efficacy of Knowledge Distillation from MWPM 评估GNN基础的量子纠错解码器是否需要经典知识 distillation
40 Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS 提出MAST框架以解决LLM-MAS通信安全漏洞问题 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🔗⭐
41 NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification 提出NeuroSync以解决用户意图与代码生成不一致问题 manipulation distillation
42 Predicting User Grasp Intentions in Virtual Reality 利用时间序列数据预测虚拟现实中的用户抓取意图 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
43 Agency, Affordances, and Enculturation of Augmentation Technologies 探讨增强技术的代理性与文化适应性 affordance

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

#题目一句话要点标签🔗⭐
44 Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network 提出DeepUFNet以解决矩形圆柱体壁面压力预测问题 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页