cs.AI（2026-07-27）

📊 共 23 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) (16 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 A Motion-Aware Vector Quantization Framework with Centroid Reuse for Efficient VLA Inference 提出VQVLA框架以解决VLA模型推理延迟问题 embodied AI vision-language-action VLA
2 Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis 提出任务条件的多模态大语言模型可信度审计框架以解决电网诊断问题 large language model multimodal
3 Making Mathematical Knowledge Explainable, Accessible and Interoperable Through Large Language Model Integration 通过大语言模型集成提升数学知识的可解释性与可访问性 large language model
4 Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory 提出对话记忆结构优化以提升大语言模型的现实监控能力 large language model
5 Generative Artificial Intelligence (GenAI) to convert images of queuing networks into verifiable simulation models: an open-weight LLM workflow approach 提出Sketch2DES以解决模拟模型构建的可验证性问题 large language model multimodal
6 Myopia Prevention and Control 3.0: Artificial Intelligence--Driven Risk Stratification, Proactive Monitoring, and Personalized Intervention 提出AI驱动的近视预防与控制新方法以应对全球近视危机 foundation model multimodal
7 ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams 提出ERUnderstand以解决ER图结构理解问题 multimodal ✅
8 Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures 提出高效的LLM生成编译器以优化复杂的捕获离子架构 large language model
9 Reason-Mediated Behavioral Models for Auditing LLM Social Simulators 提出基于理由的行为模型以审计大型语言模型的社会模拟器 large language model
10 Evaluating the Impact of Explainable AI on Trust in AI-Assisted Code Review 研究可解释人工智能对开发者信任的影响 large language model
11 LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports 提出LLM-SoccerArena以评估LLMs在体育赛事预测中的表现 large language model
12 Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models 提出HG-CRC以解决语言模型选择性预测中的风险控制问题 large language model
13 From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledge Synthesis 提出SciConsolidate以解决科学计算经验转化问题 large language model
14 DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense 提出DeepFaith以解决多阶段APT防御中的报告可信性问题 large language model
15 Simulating Tenant Responses to Energy Policy Interventions with Transaction-Cost-Aware LLM Age 提出基于交易成本感知的LLM模型以模拟租户对能源政策的反应 large language model ✅
16 Teacher Knows It Best: Spontaneous Symmetry Breaking and Tipping Points in Networked Langevin Dynamics AI Sycophancy 提出网络化随机动力学模型以应对AI引发的社会偏见问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
17 From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search 提出多智能体协议蒸馏以解决知识密集型任务的监督稀疏问题 reinforcement learning distillation large language model
18 SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents 提出SIREN框架以实现端到端极端天气预警 predictive model distillation large language model
19 Scaling GUI Agents with Visual State Transitions 提出状态转移预训练以提升GUI代理的性能 world model world models multimodal
20 EviBack: Search-Agent Reinforcement Learning via Evidence-Constrained Teacher Backoff 提出EviBack以解决多轮搜索中的信号缺失问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
21 DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models 提出DICA以解决多模态大语言模型的视觉推理问题 scene understanding large language model multimodal ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 HELIOS: An LLM-Driven Autonomous Indirect Trajectory Optimization Agent 提出HELIOS以解决低推力轨迹优化中的多重挑战 trajectory optimization large language model

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
23 Towards High-Level Semantic Intelligence 提出高层语义智能框架以提升AI认知能力 HuMoR multimodal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页