cs.AI（2026-08-11）

📊 共 27 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (19 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (3)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (19 篇)

#题目一句话要点标签🔗⭐
1 VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus 提出VERDICT以解决多模态推理验证问题 large language model multimodal
2 On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models 提出四层分类法以识别和缓解大型语言模型的安全漏洞 large language model
3 Rationale-Guided Learning for Multimodal Emotion Recognition 提出基于理由引导学习的多模态情感识别方法 multimodal
4 Expert-Guided g-computation with Large Language Models for Estimating Causal Effects on Timings: Applications to Hospital Quality Improvement 提出专家引导的g-计算方法以优化医院干预效果评估 large language model
5 Conversational versus Dashboard Explainable AI for UAV Intrusion Detection: An Empirical Study of Operator Trust and Reliance 提出对话式XAI界面以提升无人机入侵检测的操作信任度 large language model multimodal
6 Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence 提出Ex-Omni-2D以解决多模态对话生成的视觉缺失问题 multimodal
7 Why Does CLAUDE.md Keep Growing? Catastrophic Remembering in Agentic Coding 提出应对代理编码中灾难性记忆问题的解决方案 instruction following
8 Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information 提出规则法则以解决人工智能系统可解释性问题 large language model ✅
9 Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data 提出工作流卡以解决工作流执行文档不足问题 large language model
10 ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling 提出ThinkRetrieve以解决LRMs推理过程中的不确定性问题 chain-of-thought
11 Conversational Orchestration for Organic 6G 提出轻量级去中心化对话编排框架以解决Organic 6G服务问题 large language model
12 FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs 提出FITTER以解决时序知识图谱跨域推理问题 TAMP
13 HexEval: An Evidence-Driven Hexagonal Framework for Multidimensional Scholar Assessment 提出HexEval框架以解决学者评估的多维度问题 large language model
14 INSIDE the Student's Mind: Jointly Modeling Latent Reasoning and Action in LLM Student Simulators 提出INSIDE框架以解决学生模拟中的推理缺失问题 large language model
15 Continuous Interaction Diffusion: A Diffusion-Native Runtime for Asynchronous Tool-Augmented Reasoning 提出连续交互扩散以解决工具增强推理中的限制问题 large language model
16 Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation 提出人格条件化作为LLM评估敏感性探测器 large language model
17 MemSpec: Memory-Aware Runtime for Adaptive Draft Scheduling in Speculative Decoding on Edge Devices 提出MemSpec以解决边缘设备上自适应草稿调度问题 large language model
18 MazzikaAI: A knowledge-based performance-to-prompt compiler for real-time Arabic maqam accompaniment with a streaming text-to-music model 提出MazzikaAI以解决阿拉伯maqam音乐伴奏的实时生成问题 foundation model
19 Hierarchical Compositionality for An Assistive AI Agent 提出层次组合性以解决助理AI代理中的歧义问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
20 XCoT-VLA: Executable Chain-of-Thought for Vision-Language-Action Driving 提出XCoT-VLA以解决实时控制中的推理效率问题 flow matching scene understanding vision-language-action
21 SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation 提出Visual Skill Cards以解决GUI动作预测中的视觉程序记忆缺失问题 distillation multimodal
22 ComBodied Agents: a New Paradigm of Human-Centric Agentic AI 提出Combodied Agents以解决人本智能体AI的结构性缺口问题 world model world models multimodal
23 Reinforcement Learning-Based Laser Cutting Machine Parameter Optimization 提出RL²C算法以优化激光切割机参数 reinforcement learning
24 SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models 提出SKILLER以解决小型语言模型技能提取问题 reinforcement learning ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
25 Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models 提出DURA以解决VLA模型的对抗攻击问题 manipulation vision-language-action VLA
26 IO Factory: Simulating AI-Enabled Influence Campaigns at Scale 提出IO Factory以模拟大规模AI驱动的影响活动 manipulation
27 DuplexWorld: Can voice agents help you get through the day? 提出DuplexWorld以全面评估语音助手在日常生活中的应用 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页