cs.AI（2025-03-25）

📊 共 16 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) (9 🔗2) 支柱一：机器人控制 (Robot Control) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 OmniNova:A General Multimodal Agent Framework OmniNova：一种通用的多模态Agent框架，提升复杂任务自动化水平 large language model multimodal
2 Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking 上下文学习增强推理大语言模型，减少过度思考 large language model chain-of-thought
3 GENIUS: A Generative Framework for Universal Multimodal Search 提出GENIUS：一个通用的多模态搜索生成框架，提升检索效率与泛化能力。 multimodal
4 OAEI-LLM-T: A TBox Benchmark Dataset for Understanding Large Language Model Hallucinations in Ontology Matching OAEI-LLM-T：一个用于理解大型语言模型在本体匹配中幻觉现象的TBox基准数据集。 large language model
5 LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation 提出基于LLM的Agent仿真方法，用于母婴健康干预方案的不确定性评估与决策优化 large language model ✅
6 Inducing Personality in LLM-Based Honeypot Agents: Measuring the Effect on Human-Like Agenda Generation SANDMAN：利用LLM诱导人格的蜜罐代理，提升网络欺骗效果 large language model
7 Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation 提出MusiCoT：一种可分析的音乐思维链提示方法，用于高保真音乐生成 chain-of-thought ✅
8 HoarePrompt: Structural Reasoning About Program Correctness in Natural Language HoarePrompt：利用自然语言进行程序正确性的结构化推理。 large language model
9 VecTrans: Enhancing Compiler Auto-Vectorization through LLM-Assisted Code Transformations VecTrans：利用LLM辅助代码转换增强编译器自动向量化能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
10 LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning? 提出LEGO-Puzzles基准，揭示MLLM在多步空间推理上的局限性 manipulation spatial relationship large language model
11 Optimal Path Planning and Cost Minimization for a Drone Delivery System Via Model Predictive Control 提出基于模型预测控制的无人机配送系统路径优化与成本最小化方案 MPC model predictive control reinforcement learning
12 Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps Compromising Thought：操纵推理LLM的结尾Token可使其忽略正确推理步骤 manipulation large language model chain-of-thought

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
13 Taxonomy Inference for Tabular Data Using Large Language Models 提出基于大型语言模型的表格数据分类推断方法EmTT和GeTT，提升数据管理和知识发现能力。 contrastive learning large language model
14 ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning 提出ReSearch，通过强化学习训练LLM进行基于搜索的推理，无需监督数据。 reinforcement learning large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations 提出基于预训练隐式反馈的多智能体运动生成模型后训练偏好对齐方法 motion generation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
16 A Spatiotemporal Radar-Based Precipitation Model for Water Level Prediction and Flood Forecasting 提出基于时空雷达降水模型的洪水预测方法，无需上游数据依赖。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页