cs.AI（2026-08-14）

📊 共 35 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (25 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (9) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (25 篇)

#题目一句话要点标签🔗⭐
1 Grounding Without Corrective Control: Truth-Tracking Profiles for Large Language Models 提出真相追踪配置以解决大型语言模型的纠正控制问题 large language model multimodal
2 Can Language Models Understand mmWave Data? Benchmarking Large Language Models for mmWave Radar-Based Human Understanding 提出mmWave-QA以解决毫米波雷达数据理解问题 large language model language conditioned
3 Towards Efficient Multimodal and Multilingual Opinion Extraction for STI: A QLoRA-Based Fine-Tuning Approach 提出多模态核心观点提取框架以解决信息过载问题 large language model multimodal
4 A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images 提出多模态理解框架以解决科学图像解读难题 multimodal
5 Attributing Preprocessing Invariance in Spectral Foundation Models 提出谱基础模型的预处理不变性评估方法 foundation model
6 Wyvern: An Agentic Framework for Generating Grounded Multimodal Reports 提出Wyvern框架以生成多模态的基础技术报告 multimodal
7 Whose doctor does the AI recommend? An algorithm audit of reputation and demographic signals in large language model-assisted physician choice 审计算法以评估大语言模型推荐医生的偏见与透明性 large language model
8 Intern-S2-Mobius: Foundation Model with Decoupled Knowledge and Reasoning 提出Mobius架构以提升知识压缩与推理效率 foundation model
9 HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation 提出HAM-RAG以解决多模态文档生成中的结构性问题 multimodal ✅
10 Act2Intention: A Benchmark For Developing Active Mobile Agents Through Inferring User Intention from GUI Actions 提出Act2Intention框架以解决主动移动代理用户意图推断问题 large language model multimodal
11 Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers 提出Regime-Conditional Verification以解决安全分类器适应性问题 large language model
12 Handover of In-Context Learning State Across Session Boundaries 提出会话状态交接方法以解决大语言模型的上下文限制问题 large language model
13 SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning 提出SheetCompass以解决自动化电子表格推理问题 large language model
14 The Past and Future of AI Scientists 提出AI科学家以解决科学自动化整合问题 foundation model
15 LLMs Don't Pay for the Jump 提出物理成本耦合机制以解决机器推理能力不足问题 large language model
16 Tripwire: Triggering Aligned Refusal via Statistically Certified Safety Neurons 提出Tripwire以解决大语言模型的安全防护问题 large language model
17 A Hybrid LLM-Based Framework for Automated Security Annotation Generation in Business Process Models 提出混合LLM框架以自动生成业务流程模型的安全注释 large language model
18 AnchorBench: A Multi-Pathway Benchmark for the Anchoring Effect in LLMs 提出AnchorBench基准以评估LLMs中的锚定效应 large language model
19 TimeSage-EV: A Live Benchmark for Agentic Time Series Analysis in Evolving Environments 提出TimeSage-EV以解决动态环境下时间序列分析的有效性问题 large language model
20 Mandato: Protocol-Level Enforcement of Digitally Signed Mandates on AI Agent Actions with Cryptographically Chained Audit Trails 提出Mandato以解决AI代理行动授权不足问题 TAMP
21 Scaling Domain Data Repetition in LLM Pretraining 提出重复高质量领域数据以优化LLM预训练效果 large language model
22 MACS: A Hybrid Multi-Agent Framework for Reliable Conversational E-Commerce Recommendation 提出MACS框架以解决电商推荐中的可靠性问题 large language model
23 Rethinking Automated Program Repair: The Impact of Bug Complexity, Fault Localization, and LLM Cost-efficiency 提出基于LLM的自动程序修复方法以应对复杂错误问题 large language model
24 Agent-Orchestration in Autonomous Chip Design 提出AI组织模型以推动自主芯片设计的智能化 large language model
25 Never the Number: Structural Abstention for AI Systems Whose Answers Are Consumed as Fact 提出结构性拒绝机制以解决AI系统答案可靠性问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
26 Removing Temporal Note Redundancy Improves Multimodal Reinforcement Learning for Medicine 提出冗余文本去除方法以提升多模态强化学习在医疗中的应用 reinforcement learning policy learning multimodal
27 Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost 提出Traj-LeWM以解决LeWM在路径规划中的局限性 world model world models latent dynamics
28 Disentangled Shared Representations Improve Morpho-Transcriptomic Integration 提出显式解耦共享表示以改善形态转录组整合 representation learning foundation model multimodal
29 Reinforcement Learning-Based Production Scheduling in an Industry-Based Coating Scenario Using the Digital Model Playground 基于强化学习的生产调度方法解决复杂制造环境中的调度问题 reinforcement learning PPO
30 BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows 提出BGA框架以解决高熵加密流中的恶意签名提取问题 distillation
31 P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems 提出P2Skill以解决云本地LLM推理系统中的隐私保护问题 distillation
32 Reaction-Transformation-Aware Flow Matching for Generalizable Transition State Generation 提出TransTS以解决过渡态生成中的结构转化问题 flow matching
33 Twin: Playing an Unknown Game with a Test-Time Digital Twin 提出Twin系统以解决未知游戏的学习与推理问题 world model world models
34 Shift Aware Transfer Learning with Adaptive Dual-Encoder Fusion for PM Forecasting in Data-Limited Environments 提出基于双编码器融合的转移学习框架以改善PM2.5短期预测 representation learning MAE

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
35 Agentic Transaction: Towards ACID-Compliant Agent Systems 提出ACID合规的智能代理系统以解决长期任务执行问题 manipulation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页