cs.AI（2024-05-07）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Granite Code Models: A Family of Open Foundation Models for Code Intelligence 发布Granite代码模型系列，为代码智能提供开源基础模型 large language model foundation model
2 ERATTA: Extreme RAG for Table To Answers with Large Language Models 提出ERATTA，一种基于多LLM的极端RAG框架，用于企业级数据表问答，提升效率和准确性。 large language model
3 POV Learning: Individual Alignment of Multimodal Models using Human Perception 提出POV学习，利用人类感知对齐多模态模型，提升个体用户的主观预测性能。 multimodal
4 On the Foundations of Earth and Climate Foundation Models 为地球和气候科学构建理想基础模型，定义关键特征并展望未来发展方向。 foundation model
5 LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application 提出LEARN框架，利用大语言模型知识增强推荐系统，提升工业应用效果。 large language model
6 An LLM-Tool Compiler for Fused Parallel Function Calling 提出LLM-Tool Compiler，通过运行时融合工具调用优化LLM Copilot性能 large language model
7 Generative AI as a metacognitive agent: A comparative mixed-method study with human participants on ICF-mimicking exam performance 研究表明生成式AI在模拟ICF考试中表现出超越人类的元认知能力 large language model
8 A Fourth Wave of Open Data? Exploring the Spectrum of Scenarios for Open Data and Generative AI 探索开放数据与生成式AI融合的第四次浪潮，提出开放数据应用场景框架 large language model
9 NL2Plan: Robust LLM-Driven Planning from Minimal Text Descriptions NL2Plan：提出一种基于LLM的鲁棒规划方法，从极简文本描述生成PDDL任务。 large language model
10 Locally Differentially Private In-Context Learning 提出LDP-ICL框架，解决LLM在上下文学习中数据隐私泄露问题 large language model
11 TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks 提出TrimCaching：无线边缘网络中基于参数共享的AI模型缓存方案 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🔗⭐
12 Human-centric Reward Optimization for Reinforcement Learning-based Automated Driving using Large Language Models 提出基于大语言模型的人本奖励优化方法，提升强化学习自动驾驶拟人化程度。 reinforcement learning reward shaping large language model
13 Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition 提出Video-of-Thought框架，通过像素级感知到认知推理实现视频深度理解。 VIP large language model multimodal
14 Towards Continual Knowledge Graph Embedding via Incremental Distillation 提出基于增量蒸馏的知识图谱持续学习方法IncDE，有效利用图结构信息。 distillation
15 Unicorn: U-Net for Sea Ice Forecasting with Convolutional Neural Ordinary Differential Equations Unicorn：结合卷积神经常微分方程的U-Net用于海冰预测 MAE spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
16 Temporal and Heterogeneous Graph Neural Network for Remaining Useful Life Prediction 提出THGNN模型，利用时序异构图神经网络预测剩余使用寿命 spatial relationship

⬅️ 返回 cs.AI 首页 · 🏠 返回主页