cs.AI（2025-11-14）

📊 共 34 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (20 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (8) 支柱八：物理动画 (Physics-based Animation) (3) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱一：机器人控制 (Robot Control) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (20 篇)

#题目一句话要点标签🔗⭐
1 AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery AIonopedia：基于LLM的多模态学习离子液体发现平台 large language model foundation model multimodal
2 A Multimodal Manufacturing Safety Chatbot: Knowledge Base Design, Benchmark Development, and Evaluation of Multiple RAG Approaches 提出多模态安全聊天机器人，结合RAG提升制造业安全培训，并构建基准进行评估。 large language model multimodal
3 Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning 提出多智能体卧底游戏（MUG）协议，通过对抗测试消除多模态推理中的幻觉 large language model multimodal ✅
4 Differences in the Moral Foundations of Large Language Models 利用道德基础理论分析大型语言模型伦理判断差异 large language model
5 GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models 提出GGBench：一个用于统一多模态模型几何生成推理的基准测试。 multimodal ✅
6 Scaling Equitable Reflection Assessment in Education via Large Language Models and Role-Based Feedback Agents 提出基于多智能体LLM的教育反思评估系统，实现公平且可扩展的形成性反馈。 large language model
7 Constrained Network Slice Assignment via Large Language Models 利用大语言模型解决约束条件下的网络切片分配问题 large language model
8 Revisiting Disaggregated Large Language Model Serving for Performance and Energy Implications 重评估LLM解耦服务：性能与能耗影响分析及优化策略探索 large language model
9 An Analysis of Architectural Impact on LLM-based Abstract Visual Reasoning: A Systematic Benchmark on RAVEN-FAIR 系统性评估LLM在抽象视觉推理中的架构影响，基于RAVEN-FAIR数据集 large language model chain-of-thought
10 DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition 提出DialogGraph-LLM，结合图结构和LLM解决端到端音频对话意图识别问题 foundation model multimodal ✅
11 TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models TopoPerception：一种评估大视觉语言模型全局视觉感知能力的无捷径基准 large language model ✅
12 Forgetting-MarI: LLM Unlearning via Marginal Information Regularization 提出Forgetting-MarI框架，通过边际信息正则化实现LLM可证明的精确遗忘。 large language model
13 Flash-Fusion: Enabling Expressive, Low-Latency Queries on IoT Sensor Streams with LLMs Flash-Fusion：利用LLM对IoT传感器流进行低延迟、表达丰富的查询 large language model
14 Do LLMs Really Struggle at NL-FOL Translation? Revealing their Strengths via a Novel Benchmarking Strategy 提出NL-FOL翻译新基准，揭示LLM在逻辑理解上的真正能力 large language model
15 From Single to Societal: Analyzing Persona-Induced Bias in Multi-Agent Interactions 揭示LLM多智能体系统中人格偏见：信任度与坚持性分析 large language model
16 MALBO: Optimizing LLM-Based Multi-Agent Teams via Multi-Objective Bayesian Optimization MALBO：通过多目标贝叶斯优化提升基于LLM的多智能体团队性能 large language model
17 Utilizing LLMs for Industrial Process Automation: A Case Study on Modifying RAPID Programs 利用LLM修改工业机器人RAPID程序：一种少样本提示的案例研究 large language model
18 AI Agent-Driven Framework for Automated Product Knowledge Graph Construction in E-Commerce 提出AI Agent驱动的电商产品知识图谱自动构建框架，解决非结构化数据难题。 large language model
19 Do LLMs Give Good Romantic Relationship Advice? A Study on User Satisfaction and Attitude Change 研究表明，大型语言模型提供的恋爱关系建议能提升用户满意度及对LLM的积极态度。 large language model
20 Demystify, Use, Reflect: Preparing students to be informed LLM-users 设计课程培养学生批判性使用LLM的能力，应对AI辅助编程的未来 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
21 MOON Embedding: Multimodal Representation Learning for E-commerce Search Advertising MOON：用于电商搜索广告的多模态表征学习框架，CTR提升显著 representation learning multimodal
22 Large-scale modality-invariant foundation models for brain MRI analysis: Application to lesion segmentation 提出大规模模态不变脑MRI分析基础模型，应用于病灶分割 representation learning foundation model
23 STaR: Towards Effective and Stable Table Reasoning via Slow-Thinking Large Language Models STaR：通过慢思考大型语言模型实现有效且稳定的表格推理 reinforcement learning large language model
24 ARCTraj: A Dataset and Benchmark of Human Reasoning Trajectories for Abstract Problem Solving ARCTraj：用于抽象问题求解的人类推理轨迹数据集与基准 reinforcement learning PPO world model
25 Autonomous Vehicle Path Planning by Searching With Differentiable Simulation 提出基于可微仿真的搜索方法DSS，提升自动驾驶车辆路径规划精度。 imitation learning differentiable simulation
26 CURENet: Combining Unified Representations for Efficient Chronic Disease Prediction CURENet：结合统一表征的高效慢性病预测多模态模型 predictive model large language model multimodal
27 MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism MarsRL：通过强化学习与Agentic流水线并行提升多智能体推理系统 reinforcement learning large language model
28 Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis 揭示医疗AI架构中的数据投毒漏洞，分析多种攻击场景与防御挑战 reinforcement learning large language model foundation model

🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗⭐
29 Human-AI collaborative autonomous synthesis with pulsed laser deposition for remote epitaxy 提出人机协作自主合成方法，加速远程外延薄膜生长研究 PULSE large language model
30 Temporal Micro-Doppler Spectrogram-based ViT Multiclass Target Classification 提出基于时序微多普勒谱图的ViT多目标分类方法，提升毫米波雷达目标识别精度。 spatiotemporal
31 KarmaTS: A Universal Simulation Platform for Multivariate Time Series with Functional Causal Dynamics KarmaTS：用于多元时间序列的功能因果动态通用仿真平台 spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
32 Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods 综述多模态大语言模型中的空间推理：任务、基准与方法 spatial relationship 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🔗⭐
33 RLSLM: A Hybrid Reinforcement Learning Framework Aligning Rule-Based Social Locomotion Model with Human Social Norms 提出RLSLM混合强化学习框架，融合规则模型与人类社交规范，提升社交导航Agent的用户体验。 locomotion 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🔗⭐
34 Building the Web for Agents: A Declarative Framework for Agent-Web Interaction VOIX：构建面向Agent的Web，实现可靠、可审计和保护隐私的Agent-Web交互 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页