cs.AI（2026-08-13）

📊 共 37 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (22) 支柱二：RL算法与架构 (RL & Architecture) (12) 支柱一：机器人控制 (Robot Control) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement 提出数值基础框架以解决大语言模型的数值理解问题 large language model foundation model
2 DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition 提出DMDIntel以提升大语言模型预测的可解释性 large language model
3 Generative Universal Multimodal Retrieval with Dual-role Identifiers 提出DrIG框架以解决多模态检索中的效率与准确性问题 multimodal
4 SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization 提出SynAct以解决逻辑综合优化中的适应性问题 large language model
5 Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services 提出基于Stackelberg博弈的LLM服务定价与默认分配策略 large language model
6 OmniScientist: An Omni-Modal Omni-Discipline AI Scientist 提出OmniScientist以解决科学发现中的证据获取问题 foundation model
7 CAPRI: Contract-Aware Proof Repair for Isabelle 提出CAPRI以解决Isabelle证明中的合同意识问题 large language model
8 RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level 提出RAIL以自动评估人工智能技术的成熟度 large language model
9 vToken: Token-Level Virtualization for Reclaimable KV Caches 提出vToken以解决KV缓存的内存回收问题 large language model
10 TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems 提出TsuGO以评估LLM推理中的搜索效率问题 chain-of-thought
11 SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference 提出SPADE框架以解决边缘云推理的高成本与低精度问题 large language model
12 Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents 提出HARD框架以实现自我演化的LLM代理防御机制 large language model
13 Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference 提出E2-Explainer以解决LLM多智能体系统通信拓扑可解释性问题 large language model
14 Memorization Diagnostics for Code LLMs Should be Scale-Aware 提出规模感知的记忆诊断方法以解决代码LLM的理解问题 large language model
15 PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs 提出PROVE-RT以解决实时系统的可调度性分析问题 large language model
16 Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks 提出一种新型水印技术以解决LLM文本溯源与篡改检测问题 large language model
17 Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs 提出SEAG框架以保护RAG中的敏感信息 large language model
18 On the Expressive Power of Transformers 通过电路复杂性分析变换器的表达能力 large language model
19 SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization 提出SynAct以解决逻辑综合优化中的适应性问题 large language model
20 Simulation-Aware In-Context Policy Improvement for LLM-Aided Analog Layout Refinement 提出基于仿真的LLM多智能体框架以优化模拟电路布局 large language model
21 Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT 提出三阶段微调方案以解决C到Rust代码翻译问题 large language model
22 Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference 提出E2-Explainer以解决LLM多智能体系统通信拓扑可解释性问题 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🔗⭐
23 FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving 提出FlashDrive以解决自主驾驶中的VLA推理延迟问题 flow matching vision-language-action VLA
24 A Unifying Perspective on Causal World Models: From Observations to Representations to Structure 提出因果世界模型以提升智能体的预测与决策能力 world model world models representation learning
25 The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis 提出基于YOLO和CLIP的多模态框架以解决登革热病毒蚊子检测问题 contrastive learning multimodal
26 EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding 提出EEG-PRIME以解决EEG解码中的跨数据集泛化问题 representation learning foundation model zero-shot transfer
27 AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1) 提出AlayaWorld以改进长时间世界建模的条件信号整合 world model world models
28 OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways 提出OGR-MARL框架以解决异构USV在港口水域的协同追捕问题 reinforcement learning policy learning zero-shot transfer
29 Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence 提出空间记忆代理以解决空间智能推理问题 reinforcement learning depth estimation 3D reconstruction
30 Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds 通过行为重编程提升开放权重模型的认知灵活性 DPO direct preference optimization large language model
31 Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies 提出进化策略以提升大型语言模型的解答覆盖率 reinforcement learning large language model
32 Rules or Character? Scaling Laws for AI Safety Design 提出安全设计的资源分配模型以优化AI安全性 reinforcement learning RLHF
33 Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents 提出CrEST框架以解决多轮工具使用代理的信用分配问题 reinforcement learning distillation
34 Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning 提出MCJEPA以实现隐马尔可夫模型的状态空间解释 JEPA

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
35 Error-Aware Reverse Auction Mechanism for Large Language Model Routing 提出错误感知反向拍卖机制以优化大语言模型路由 manipulation large language model
36 Coverage Aware Active Evaluation for Failure Discovery with Paired Systems 提出覆盖感知主动评估方法以发现系统故障 quadruped manipulation sim-to-real

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

#题目一句话要点标签🔗⭐
37 Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision 提出基于自我中心视觉的运动理解方法以解决日常生活中的步态冻结检测问题 egocentric egocentric vision foundation model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页