cs.AI（2023-10-03）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱一：机器人控制 (Robot Control) (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 Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond 提出多模态大语言模型以提升具身决策能力 large language model multimodal ✅
2 Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models 提出Selenite以解决信息领域冷启动问题 large language model
3 An evolutionary model of personality traits related to cooperative behavior using a large language model 提出基于大语言模型的个性特征进化模型以研究合作行为 large language model
4 Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions? 提出nl2postcond以将自然语言意图转化为形式化后置条件 large language model
5 HPC-GPT: Integrating Large Language Model for High-Performance Computing 提出HPC-GPT以解决高性能计算领域的语言模型应用问题 large language model
6 Conceptual Framework for Autonomous Cognitive Entities 提出自主认知实体模型以提升机器独立性 large language model multimodal
7 Lyfe Agents: Generative agents for low-cost real-time social interactions 提出Lyfe Agents以解决低成本实时社交互动问题 large language model
8 AXNav: Replaying Accessibility Tests from Natural Language 提出AXNav以解决无障碍测试的自动化问题 large language model
9 Can GPT-4 Replicate Empirical Software Engineering Research? 探讨GPT-4在软件工程实证研究中的复制能力 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🔗⭐
10 Prompting Audios Using Acoustic Properties For Emotion Representation 提出基于声学特征的提示生成方法以改善情感表示 contrastive learning motion representation
11 Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI 提出Mini-BEHAVIOR以解决长时间决策问题 reinforcement learning embodied AI ✅
12 Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning 提出优先软Q分解以解决连续空间的多目标强化学习问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model 提出AlignDiff以解决人类偏好的对齐问题 locomotion reinforcement learning RLHF ✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页