cs.AI（2024-03-13）

📊 共 16 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) (9) 支柱一：机器人控制 (Robot Control) (4) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Foundation Models and Information Retrieval in Digital Pathology 综述基础模型在数字病理学中的信息检索应用 foundation model
2 A Moral Imperative: The Need for Continual Superalignment of Large Language Models 提出持续超对齐框架以解决大型语言模型的伦理适应问题 large language model
3 Bugs in Large Language Models Generated Code: An Empirical Study 识别大型语言模型生成代码中的错误模式以提升代码质量 large language model
4 AcademiaOS: Automating Grounded Theory Development in Qualitative Research with Large Language Models 提出AcademiaOS以自动化定性研究中的基础理论发展 large language model
5 AutoTRIZ: Automating Engineering Innovation with TRIZ and Large Language Models 提出AutoTRIZ以自动化TRIZ方法解决工程创新问题 large language model
6 Software Vulnerability and Functionality Assessment using LLMs 利用大型语言模型提升软件漏洞与功能评估效率 large language model chain-of-thought
7 Exploring Prompt Engineering Practices in the Enterprise 探讨企业中的提示工程实践以提升LLM交互效率 large language model
8 Teaching Machines to Code: Smart Contract Translation with LLMs 提出SolMover以解决智能合约翻译问题 large language model
9 Search-based Optimisation of LLM Learning Shots for Story Point Estimation 提出基于搜索优化的少量学习方法以提升故事点估算精度 large language model

🔬 支柱一：机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗⭐
10 Cultural evolution in populations of Large Language Models 提出利用大型语言模型模拟文化演化以解决现有模型不足问题 manipulation large language model
11 Distract Large Language Models for Automatic Jailbreak Attack 提出黑箱监狱突破框架以自动化攻击大型语言模型 manipulation large language model
12 Strategizing against Q-learners: A Control-theoretical Approach 提出控制理论方法应对Q学习者的策略操控问题 manipulation reinforcement learning
13 AutoDev: Automated AI-Driven Development 提出AutoDev以解决软件开发自动化不足问题 manipulation

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

#题目一句话要点标签🔗⭐
14 Meta-operators for Enabling Parallel Planning Using Deep Reinforcement Learning 提出元操作符以解决深度强化学习中的并行规划问题 reinforcement learning deep reinforcement learning
15 Beyond Joint Demonstrations: Personalized Expert Guidance for Efficient Multi-Agent Reinforcement Learning 提出个性化专家指导以解决多智能体强化学习中的探索效率问题 reinforcement learning

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

#题目一句话要点标签🔗⭐
16 GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting 提出GaussianImage以解决低端设备图像表示与压缩问题 gaussian splatting splatting ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页