cs.AI（2024-12-19）

📊 共 21 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (16) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#	题目	一句话要点	标签	🔗	⭐
1	IOHunter: Graph Foundation Model to Uncover Online Information Operations	IOHunter：图神经网络基础模型揭示在线信息操纵行为	foundation model
2	FaultExplainer: Leveraging Large Language Models for Interpretable Fault Detection and Diagnosis	FaultExplainer：利用大语言模型实现可解释的故障检测与诊断	large language model
3	Relational Programming with Foundation Models	Vieira：一种基于关系编程的框架，用于统一和增强基础模型。	foundation model
4	Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying	利用论证查询中的批判性问题，引导LLM进行更有效的推理	large language model chain-of-thought
5	Bridging the Data Provenance Gap Across Text, Speech and Video	大规模多模态数据集溯源分析，揭示数据来源、限制与代表性问题	multimodal
6	A Unified Framework for Context-Aware IoT Management and State-of-the-Art IoT Traffic Anomaly Detection	提出基于上下文感知的物联网管理框架，并实现物联网流量异常检测。	large language model
7	Automated Root Cause Analysis System for Complex Data Products	提出ARCAS自动化根因分析系统，加速复杂数据产品问题诊断与修复。	large language model
8	Associative memory inspires improvements for in-context learning using a novel attention residual stream architecture	受联想记忆启发，提出新型注意力残差流架构以提升上下文学习能力	large language model
9	From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security	系统性文献综述：大型语言模型在代码安全中的漏洞与修复	large language model
10	HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs	HSEvo：利用多样性驱动的和谐搜索与遗传算法提升基于LLM的自动启发式设计	large language model
11	Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?	分析通用AI模型部署中的安全风险，借鉴网络安全经验提出应对策略	large language model
12	Helping LLMs Improve Code Generation Using Feedback from Testing and Static Analysis	利用测试与静态分析反馈提升LLM代码生成质量与安全性	large language model
13	Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling	提出Tree-of-Code框架，用于复杂任务中端到端代码生成与执行，提升LLM推理能力。	large language model
14	Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization	结合零样本学习与MaxSAT故障定位，提升LLM在程序自动修复中的性能	large language model
15	Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey	综述AI驱动的智能空间，提升室内环境质量与用户体验	large language model
16	Beyond the Sum: Unlocking AI Agents Potential Through Market Forces	分析AI Agent在数字市场中自主运行的基础设施需求	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
17	Deep reinforcement learning with time-scale invariant memory	提出基于时间尺度不变记忆的深度强化学习，提升Agent在不同时间尺度下的鲁棒性。	reinforcement learning deep reinforcement learning
18	Agent-Temporal Credit Assignment for Optimal Policy Preservation in Sparse Multi-Agent Reinforcement Learning	提出TAR$^2$方法，解决稀疏多智能体强化学习中的信用分配问题，提升策略学习效率。	reinforcement learning reward shaping
19	The impact of behavioral diversity in multi-agent reinforcement learning	研究行为多样性对多智能体强化学习的影响，提升团队协作能力	reinforcement learning
20	Investigating Relational State Abstraction in Collaborative MARL	提出MARC，利用空间关系抽象提升协作多智能体强化学习的样本效率和性能。	reinforcement learning spatial relationship

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
21	LTLf Synthesis Under Unreliable Input	针对不可靠输入下的LTLf目标，提出策略综合方法以确保备用规范	manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页