cs.AI（2023-10-11）

📊 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) (10) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 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 Toward Understanding BERT-Like Pre-Training for DNA Foundation Models 提出RandomMask方法以解决DNA序列预训练不足问题 foundation model
2 Beyond Memorization: Violating Privacy Via Inference with Large Language Models 研究大型语言模型推断个人属性以解决隐私问题 large language model
3 Hierarchical Pretraining on Multimodal Electronic Health Records 提出MEDHMP框架以解决电子健康记录的层次化预训练问题 multimodal
4 Mini-DALLE3: Interactive Text to Image by Prompting Large Language Models 提出Mini-DALLE3以解决文本到图像交互生成问题 large language model
5 OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models 提出OpsEval基准以评估大语言模型在IT运维中的表现 large language model
6 Multimodal Graph Learning for Generative Tasks 提出多模态图学习框架以解决生成任务中的复杂关系建模问题 multimodal
7 An Analysis on Large Language Models in Healthcare: A Case Study of BioBERT 通过BioBERT提升医疗领域自然语言处理能力 large language model
8 MatChat: A Large Language Model and Application Service Platform for Materials Science 提出MatChat以解决材料科学中化学合成路径预测问题 large language model
9 ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations 提出ClausewitzGPT框架以应对信息操作中的AI挑战 large language model
10 AutoRepo: A general framework for multi-modal LLM-based automated construction reporting 提出AutoRepo框架以解决建筑检查报告自动化问题 large language model multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
11 DeePref: Deep Reinforcement Learning For Video Prefetching In Content Delivery Networks 提出DeePref以解决视频预取在内容分发网络中的挑战 reinforcement learning deep reinforcement learning
12 Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning 提出LaHA框架以解决少样本学习中的硬注意力问题 reinforcement learning deep reinforcement learning
13 Online Speculative Decoding 提出在线推测解码以提升大语言模型推理效率 distillation large language model ✅
14 Reinforcement Learning-based Knowledge Graph Reasoning for Explainable Fact-checking 提出基于强化学习的知识图谱推理方法以实现可解释的事实核查 reinforcement learning
15 Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization 提出影响程度指标以解决多智能体强化学习中的泛化问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 RoboCLIP: One Demonstration is Enough to Learn Robot Policies 提出RoboCLIP以解决强化学习中的奖励指定问题 manipulation reinforcement learning imitation learning

⬅️ 返回 cs.AI 首页 · 🏠 返回主页