cs.AI（2024-08-02）

📊 共 14 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) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks 综述多模态大语言模型在不同任务中的性能与挑战，并展望未来研究方向 large language model multimodal
2 Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models Piculet：利用专业模型引导，降低多模态大语言模型的幻觉 large language model multimodal
3 Telecom Foundation Models: Applications, Challenges, and Future Trends 提出电信基础模型（TFMs），解决电信网络复杂性带来的管理、优化难题。 foundation model
4 LibreLog: Accurate and Efficient Unsupervised Log Parsing Using Open-Source Large Language Models LibreLog：利用开源大语言模型实现高精度、高效率的无监督日志解析 large language model
5 Dissecting Dissonance: Benchmarking Large Multimodal Models Against Self-Contradictory Instructions 提出自相矛盾指令基准，揭示并缓解大模型在多模态冲突指令识别上的不足。 multimodal ✅
6 Semantic Skill Grounding for Embodied Instruction-Following in Cross-Domain Environments 提出语义技能基础框架以解决跨领域指令跟随问题 instruction following
7 ArchCode: Incorporating Software Requirements in Code Generation with Large Language Models ArchCode：利用大语言模型将软件需求融入代码生成 large language model
8 A General-Purpose Device for Interaction with LLMs 提出通用设备以增强与大型语言模型的交互 large language model multimodal
9 LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems 提出Healer框架，利用LLM实时处理运行时错误，实现软件系统自愈 large language model
10 On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents 研究LLM多智能体协作系统在故障智能体下的鲁棒性，并提出Challenger和Inspector机制提升系统韧性。 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🔗⭐
11 Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems 提出基于深度W学习的多目标强化学习方法，用于自治系统中运行时性能优化。 reinforcement learning deep reinforcement learning
12 Optimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement Learning 利用元启发式算法优化变分量子电路，提升量子强化学习性能 reinforcement learning
13 A Survey on Self-play Methods in Reinforcement Learning 综述性研究：全面解析强化学习中自博弈方法的原理、应用与未来方向 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Detection and Characterization of Coordinated Online Behavior: A Survey 综述协同网络行为检测与表征方法，为理解和应对在线协同提供指导。 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页