cs.AI（2024-05-30）

📊 共 32 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) (24 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (24 篇)

#题目一句话要点标签🔗⭐
1 Research on the Spatial Data Intelligent Foundation Model 探索空间数据智能大模型，赋能城市、遥感、交通等领域应用 foundation model multimodal
2 Efficient LLM-Jailbreaking via Multimodal-LLM Jailbreak 提出一种基于多模态LLM越狱的高效LLM越狱方法，提升攻击效率和泛化性。 large language model multimodal
3 PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization 提出PostDoc，利用深度子模优化从长多模态文档中自动生成海报 multimodal
4 Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning 研究编码数据指令微调对大语言模型推理能力的影响 large language model
5 SECURE: Benchmarking Large Language Models for Cybersecurity SECURE：面向网络安全的LLM基准测试，聚焦工控系统 large language model
6 Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA 揭示医学VQA中大型多模态模型在诊断问题上表现甚至不如随机猜测，并提出ProbMed基准。 multimodal
7 Designing an Evaluation Framework for Large Language Models in Astronomy Research 构建天文学领域大语言模型评估框架，促进科研应用 large language model
8 A Survey Study on the State of the Art of Programming Exercise Generation using Large Language Models 调研大型语言模型在编程练习生成中的应用现状，并提出评估矩阵。 large language model
9 LLaMEA: A Large Language Model Evolutionary Algorithm for Automatically Generating Metaheuristics LLaMEA：基于大语言模型进化算法的元启发式算法自动生成框架 large language model
10 KNOW: A Real-World Ontology for Knowledge Capture with Large Language Models 提出KNOW：一个现实世界知识本体，用于利用大型语言模型捕获知识，应用于个人AI助手等场景。 large language model
11 Deciphering Human Mobility: Inferring Semantics of Trajectories with Large Language Models 提出TSI-LLM框架，利用大语言模型推断轨迹语义，解决人类移动模式理解难题 large language model
12 Grade Like a Human: Rethinking Automated Assessment with Large Language Models 提出基于LLM的自动化评分系统，模拟人类评分全流程，提升复杂问题评分质量 large language model
13 Knowledge Graph Tuning: Real-time Large Language Model Personalization based on Human Feedback 提出知识图谱调优（KGT）方法，实现基于人类反馈的实时大语言模型个性化。 large language model
14 Large Language Model Watermark Stealing With Mixed Integer Programming 提出基于混合整数规划的大语言模型水印窃取攻击，有效破解现有水印方案。 large language model
15 Unlocking the Power of Spatial and Temporal Information in Medical Multimodal Pre-training Med-ST：融合时空信息的医学多模态预训练框架，提升医学影像报告理解能力 multimodal ✅
16 Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router 提出基于智能路由的开源大语言模型系统，用于高效编码健康社会决定因素（SDOH）。 large language model
17 Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases 提出一种探针与恢复框架，利用源码大模型提升二进制代码分析效果 foundation model
18 An Automatic Question Usability Evaluation Toolkit 提出SAQUET工具包，利用大型语言模型自动评估多选题质量，解决传统方法忽略深层设计缺陷的问题。 large language model
19 Automated Generation and Tagging of Knowledge Components from Multiple-Choice Questions 利用GPT-4自动生成和标注多选题的知识组件，提升教学评估效率。 large language model
20 Diffusion On Syntax Trees For Program Synthesis 提出基于语法树扩散模型的程序合成方法，解决代码生成缺乏反馈的问题。 large language model
21 Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions 通过事实性评分和来源归属促进人与大型语言模型的协作 large language model
22 Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Models 提出LLM引导的遗传算法，实现交互式语言模型中聊天记录篡改，提升模型可塑性。 large language model
23 One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient Deployments 提出One QuantLLM for ALL框架，通过一次量化微调实现LLM在不同资源约束下的高效部署。 large language model
24 Easy Problems That LLMs Get Wrong 构建语言基准测试，揭示大型语言模型在简单问题上的局限性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
25 MSSC-BiMamba: Multimodal Sleep Stage Classification and Early Diagnosis of Sleep Disorders with Bidirectional Mamba 提出MSSC-BiMamba模型，利用双向Mamba网络进行多模态睡眠分期和睡眠障碍早期诊断。 Mamba state space model multimodal
26 A Deep Reinforcement Learning Approach for Trading Optimization in the Forex Market with Multi-Agent Asynchronous Distribution 提出基于多智能体异步深度强化学习的外汇交易优化方法 reinforcement learning deep reinforcement learning DRL
27 Relation Modeling and Distillation for Learning with Noisy Labels 提出RMDNet，通过关系建模与知识蒸馏提升噪声标签下的学习鲁棒性 representation learning contrastive learning distillation
28 Efficient Stimuli Generation using Reinforcement Learning in Design Verification 提出一种基于强化学习的高效激励生成方法，加速SoC设计的验证覆盖率。 reinforcement learning
29 Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity 提出一种无需下层凸性的双层强化学习超梯度方法 reinforcement learning
30 Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf 提出基于强化学习指导的语言智能体框架，用于解决“一夜终极狼人杀”中的策略性讨论问题 reinforcement learning large language model
31 Federated Cross-Training Learners for Robust Generalization under Data Heterogeneity 提出FedCT，通过多视角知识蒸馏解决联邦学习中的数据异构问题。 representation learning distillation

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
32 Effects of Dataset Sampling Rate for Noise Cancellation through Deep Learning 研究数据集采样率对基于深度学习的噪声消除效果的影响，优化移动设备端语音质量。 WHAM

⬅️ 返回 cs.AI 首页 · 🏠 返回主页