cs.AI（2025-07-26）

📊 共 14 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Leveraging Fine-Tuned Large Language Models for Interpretable Pancreatic Cystic Lesion Feature Extraction and Risk Categorization 利用微调的大语言模型实现可解释的胰腺囊性病变特征提取与风险分级 large language model chain-of-thought
2 AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks AgentTTS：基于LLM Agent的多阶段复杂任务测试时计算最优缩放策略 large language model
3 The Impact of Fine-tuning Large Language Models on Automated Program Repair 研究微调大型语言模型对自动化程序修复性能的影响，并提出参数高效微调策略。 large language model
4 Matching Game Preferences Through Dialogical Large Language Models: A Perspective 提出基于对话式大语言模型的偏好匹配框架，提升AI决策透明度 large language model
5 Improving the Performance of Sequential Recommendation Systems with an Extended Large Language Model 通过扩展大型语言模型Llama3，提升序列推荐系统性能 large language model
6 CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation CrossPL：首个跨编程语言代码生成能力评测基准 large language model
7 PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training PITA：通过偏好引导的推理时对齐方法，无需奖励模型即可优化LLM large language model
8 The Carbon Cost of Conversation, Sustainability in the Age of Language Models 量化大型语言模型碳足迹，呼吁可持续的自然语言处理 large language model
9 SmartCourse: A Contextual AI-Powered Course Advising System for Undergraduates SmartCourse：一个基于情境感知的AI本科课程推荐系统 large language model
10 AgentMesh: A Cooperative Multi-Agent Generative AI Framework for Software Development Automation AgentMesh：一种用于软件开发自动化的协同多智能体生成式AI框架 large language model
11 Can LLMs Solve ASP Problems? Insights from a Benchmarking Study (Extended Version) ASPBench：构建ASP基准测试，揭示LLM在解答集编程中的局限性 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
12 Reinforcement Learning for Multi-Objective Multi-Echelon Supply Chain Optimisation 提出基于多目标强化学习的多级供应链优化模型，解决非稳态市场下的经济、环境和社会目标权衡问题。 reinforcement learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
13 Policy-Driven AI in Dataspaces: Taxonomy, Explainability, and Pathways for Compliant Innovation 提出面向数据空间的策略驱动AI框架，实现合规创新 OMOMO

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

#题目一句话要点标签🔗⭐
14 Integrating Activity Predictions in Knowledge Graphs 提出基于知识图谱和马尔可夫链的活动预测方法，用于预测未来事件。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页