cs.AI（2024-07-11）

📊 共 27 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (21 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (21 篇)

#题目一句话要点标签🔗⭐
1 GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration GeNet：基于多模态LLM的企业网络拓扑与配置协同助手 large language model multimodal
2 Incorporating Large Language Models into Production Systems for Enhanced Task Automation and Flexibility 提出一种集成LLM的生产系统，提升任务自动化和灵活性 large language model ✅
3 The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective 综述多模态大语言模型与数据协同发展，促进模型能力提升与数据质量优化。 large language model ✅
4 Paving the way toward foundation models for irregular and unaligned Satellite Image Time Series ALISE：面向不规则卫星图像时间序列的基础模型对齐编码器 foundation model
5 Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On Skywork-Math：通过数据规模扩展提升大语言模型数学推理能力 large language model
6 Foundation Model Engineering: Engineering Foundation Models Just as Engineering Software 提出基础模型工程，应对基础模型日益增长的复杂性挑战。 foundation model
7 The Career Interests of Large Language Models 利用职业兴趣量表探索大语言模型的职业倾向与能力，揭示其在职场中的潜在角色。 large language model
8 On the attribution of confidence to large language models 探讨大语言模型置信度归因的合理性与可靠性 large language model
9 Towards Explainable Evolution Strategies with Large Language Models 提出基于大语言模型的可解释进化策略，提升复杂优化过程透明度 large language model
10 Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments 提出Continual Visual Mapping (CVM)，在资源受限环境下持续学习视觉概念到大型语言模型的映射 large language model
11 SoupLM: Model Integration in Large Language and Multi-Modal Models SoupLM：通过模型融合策略高效构建通用多模态大语言模型 large language model multimodal
12 Have We Reached AGI? Comparing ChatGPT, Claude, and Gemini to Human Literacy and Education Benchmarks LLM在教育基准测试中超越人类，逼近通用人工智能（AGI） large language model
13 Privacy-Preserving Data Deduplication for Enhancing Federated Learning of Language Models (Extended Version) 提出EP-MPD协议，解决联邦学习中语言模型数据去重的隐私保护问题。 large language model
14 AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies 提出AIR-Bench 2024，一个基于法规和政策风险类别的AI安全基准。 foundation model
15 Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion 利用语言模型评估德国公众意见：GPT-3.5在预测选民投票选择方面存在偏差 large language model
16 Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents LLM赋能的自主Agent融合符号主义与连接主义AI范式，提升推理与决策能力 large language model
17 Lynx: An Open Source Hallucination Evaluation Model 提出LYNX，一个开源幻觉评估模型，并在HaluBench基准测试中超越GPT-4o。 large language model
18 Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation 提出多模态生成AI框架，提升Verilog代码生成精度，解决自然语言描述硬件设计不足问题。 large language model
19 Toward accessible comics for blind and low vision readers 提出一种利用提示工程和上下文信息生成漫画故事文本描述的方法，为视障读者提供可访问的漫画内容。 large language model
20 Leveraging LLMs to Predict Affective States via Smartphone Sensor Features 利用大型语言模型和智能手机传感器数据预测情感状态 large language model
21 A Text-to-Game Engine for UGC-Based Role-Playing Games 提出基于文本到游戏引擎的框架Zagii，利用生成式AI赋能UGC角色扮演游戏 foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
22 Multimodal contrastive learning for spatial gene expression prediction using histology images 提出mclSTExp，利用多模态对比学习预测空间基因表达，提升预测精度。 contrastive learning multimodal ✅
23 $β$-DPO: Direct Preference Optimization with Dynamic $β$ 提出动态β调整的DPO方法，提升LLM对齐人类偏好的鲁棒性和适应性。 DPO direct preference optimization large language model ✅
24 Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks 提出HC-MARL框架，通过分层共识机制提升多智能体强化学习在多机器人协作任务中的性能。 reinforcement learning contrastive learning
25 Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing 模型手术：通过简单参数编辑调控LLM行为 reinforcement learning RLHF large language model
26 A Review of Nine Physics Engines for Reinforcement Learning Research 综述九种强化学习物理引擎，为研究者选择模拟环境提供指导 reinforcement learning
27 ST-Mamba: Spatial-Temporal Mamba for Traffic Flow Estimation Recovery using Limited Data 提出ST-Mamba模型，利用有限数据实现精准稳定的交通流量估计与恢复。 Mamba

⬅️ 返回 cs.AI 首页 · 🏠 返回主页