cs.AI（2025-04-06）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 How Accurately Do Large Language Models Understand Code? 通过缺陷定位评估，揭示大语言模型对代码理解的局限性 large language model
2 DDPT: Diffusion-Driven Prompt Tuning for Large Language Model Code Generation 提出DDPT，利用扩散模型自动优化大语言模型代码生成的提示词嵌入。 large language model
3 Crowdsourcing-Based Knowledge Graph Construction for Drug Side Effects Using Large Language Models with an Application on Semaglutide 利用大型语言模型和众包构建药物副作用知识图谱，以司美格鲁肽为例。 large language model
4 AdaptRec: A Self-Adaptive Framework for Sequential Recommendations with Large Language Models AdaptRec：一种基于大语言模型的自适应序列推荐框架 large language model
5 Universal Item Tokenization for Transferable Generative Recommendation 提出UTGRec，一种通用项目标记化方法，用于可迁移的生成式推荐。 large language model multimodal
6 Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification 提出结合知识图谱RAG与符号验证的分层规划方法，提升LLM在复杂任务中的规划能力 large language model
7 Exploring Generative AI Techniques in Government: A Case Study 构建智能代理Pubbie，利用生成式AI赋能政府部门绩效评估与数据管理 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
8 AI2STOW: End-to-End Deep Reinforcement Learning to Construct Master Stowage Plans under Demand Uncertainty AI2STOW：基于深度强化学习的端到端配载方案生成，解决需求不确定性下的船舶积载问题 reinforcement learning deep reinforcement learning
9 AI in a vat: Fundamental limits of efficient world modelling for agent sandboxing and interpretability 针对AI Agent沙盒测试，提出效率与可解释性权衡的世界模型简化方法 world model
10 Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks 提出基于地标分层强化学习方法，解决Sokoban游戏难题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
11 A Survey of Social Cybersecurity: Techniques for Attack Detection, Evaluations, Challenges, and Future Prospects 综述社交网络安全：攻击检测技术、评估、挑战与未来展望 manipulation
12 Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond 构建LLM注意力机制的物理理论，解析重复、幻觉和偏见等问题 manipulation
13 AGITB: A Signal-Level Benchmark for Evaluating Artificial General Intelligence AGITB：一个用于评估通用人工智能的信号级基准测试 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
14 EclipseNETs: Learning Irregular Small Celestial Body Silhouettes 提出EclipseNETs，利用神经隐式表示高效预测不规则小天体周围的日食事件 implicit representation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页