cs.AI（2024-06-19）

📊 共 20 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)

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

#	题目	一句话要点	标签	🔗	⭐
1	Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency	全面评测GPT-4o在语言、视觉、语音和多模态能力上的表现	large language model multimodal
2	Converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion	提出一种多源、多模态、多语言融合的信息抽取与摘要方法，克服现有方法依赖单一数据源的局限性。	large language model multimodal
3	APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts	APPL：一种提示编程语言，用于程序与大语言模型提示的和谐集成	large language model chain-of-thought
4	BEACON: Balancing Convenience and Nutrition in Meals With Long-Term Group Recommendations and Reasoning on Multimodal Recipes	BEACON：结合长期群体推荐与多模态食谱推理，平衡膳食的便利性与营养	multimodal
5	Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health	利用大型语言模型赋能患者互动：会话式AI在数字健康中的力量	large language model
6	Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?	在囚徒困境中LLM表现优于人类：评估AI代理的合作行为与价值观	large language model
7	Enhancing Travel Choice Modeling with Large Language Models: A Prompt-Learning Approach	提出基于Prompt Learning的大语言模型框架，提升出行选择建模的精度和可解释性	large language model
8	LLMatDesign: Autonomous Materials Discovery with Large Language Models	LLMatDesign：利用大语言模型实现自主材料发现	large language model
9	Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization	提出组合推理（CR）框架，通过组合优化提升生成式AI管道的推理能力。	large language model chain-of-thought
10	A Pure Transformer Pretraining Framework on Text-attributed Graphs	提出GSPT：一种纯Transformer的文本属性图预训练框架，提升图间迁移能力。	large language model
11	Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data	构建生成式AI滥用策略分类体系，揭示真实世界滥用案例	multimodal
12	StackRAG Agent: Improving Developer Answers with Retrieval-Augmented Generation	提出StackRAG Agent，利用检索增强生成提升开发者问答质量	large language model
13	On AI-Inspired UI-Design	提出AI驱动的UI设计流程，利用LLM、VLM和扩散模型激发设计灵感，提升UI设计质量和多样性。	large language model
14	Investigating Low-Cost LLM Annotation for~Spoken Dialogue Understanding Datasets	利用低成本LLM标注增强口语对话理解数据集的语义表示	large language model
15	LangTopo: Aligning Language Descriptions of Graphs with Tokenized Topological Modeling	提出LangTopo框架，通过token级对齐实现LLM对图拓扑结构的建模能力	large language model
16	Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference	Amphista：一种双向多头解码方法，加速LLM推理。	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	CoDreamer: Communication-Based Decentralised World Models	CoDreamer：一种基于通信的去中心化世界模型，用于多智能体强化学习。	reinforcement learning world model dreamer
18	Cardiac Copilot: Automatic Probe Guidance for Echocardiography with World Model	提出Cardiac Copilot系统，利用世界模型辅助非专业人员进行超声心动图检查。	world model dreamer
19	Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks	提出基于梯形梯度下降的SNN强化学习算法，提升训练效果	reinforcement learning
20	VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework	提出VELO框架，利用向量数据库在云边协同环境中优化LLM的QoS。	reinforcement learning large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页