cs.AI（2024-08-20）

📊 共 28 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) (18) 支柱二：RL算法与架构 (RL & Architecture) (7) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (18 篇)

#题目一句话要点标签🔗⭐
1 Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches 针对边缘设备LLM微调与部署，综述高效微调与压缩技术 large language model foundation model
2 Out-of-Distribution Detection with Attention Head Masking for Multimodal Document Classification 提出注意力头掩码(AHM)方法，用于多模态文档分类中的OOD检测。 multimodal
3 From Glucose Patterns to Health Outcomes: A Generalizable Foundation Model for Continuous Glucose Monitor Data Analysis GluFormer：基于连续血糖监测数据的通用基础模型，用于预测健康结果 foundation model
4 What can Large Language Models Capture about Code Functional Equivalence? SeqCoBench：评估代码大语言模型对代码功能等价性理解能力的基准 large language model
5 LeCov: Multi-level Testing Criteria for Large Language Models LeCov：面向大语言模型的多层次测试准则，提升模型可信度。 large language model
6 Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles 提出基于载体文章的黑盒越狱方法，提升大语言模型安全性 large language model
7 Reconciling Methodological Paradigms: Employing Large Language Models as Novice Qualitative Research Assistants in Talent Management Research 利用RAG-LLM作为新手研究助理，提升人才管理研究中定性数据分析效率。 large language model
8 Dr.Academy: A Benchmark for Evaluating Questioning Capability in Education for Large Language Models 提出Dr.Academy基准，评估大型语言模型在教育领域的问题生成能力 large language model
9 Large Language Model Driven Recommendation 利用大型语言模型驱动的推荐系统，实现个性化和交互式推荐。 large language model
10 Flexora: Flexible Low Rank Adaptation for Large Language Models Flexora：一种灵活的低秩自适应方法，用于提升大语言模型在下游任务上的性能。 large language model
11 Fine-Tuning a Local LLaMA-3 Large Language Model for Automated Privacy-Preserving Physician Letter Generation in Radiation Oncology 通过本地微调LLaMA-3大语言模型，实现辐射肿瘤科的自动化隐私保护型医生信函生成。 large language model
12 Investigating Context Effects in Similarity Judgements in Large Language Models 研究大型语言模型在相似性判断中受上下文效应的影响 large language model
13 Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation 提出JVD方法，通过生成不安全解码路径探测并利用大语言模型的安全漏洞。 large language model
14 How Well Do Large Language Models Serve as End-to-End Secure Code Agents for Python? 评估大型语言模型作为端到端安全Python代码生成器的能力，并提出迭代修复工具。 large language model
15 Pluto and Charon: A Time and Memory Efficient Collaborative Edge AI Framework for Personal LLMs Fine-Tuning Pluto and Charon：一种时间与内存高效的边缘AI协同框架，用于个人LLM微调 large language model
16 Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm 提出EPiC：利用进化算法进行低成本代码生成提示工程 large language model
17 Towards Efficient Formal Verification of Spiking Neural Network 提出基于时间编码的高效SNN形式化验证方法，提升对抗鲁棒性验证的可扩展性。 large language model
18 AI-Based IVR 提出基于AI的IVR系统，提升呼叫中心效率并适配哈萨克语 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🔗⭐
19 OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation OCTCube-M：用于视网膜和全身疾病的3D多模态OCT基础模型 contrastive learning foundation model multimodal
20 QPO: Query-dependent Prompt Optimization via Multi-Loop Offline Reinforcement Learning 提出QPO以解决查询依赖的提示优化问题 reinforcement learning offline reinforcement learning large language model
21 Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks Hokoff：王者荣耀真实游戏数据集及其离线强化学习基准 reinforcement learning offline RL offline reinforcement learning
22 MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling 提出MambaDS模型，利用地形约束选择性状态空间建模实现近地面气象场降尺度 Mamba state space model
23 Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation 提出MinorSFT损失函数，提升SFT微调效果并降低LLM模型偏移 PPO RLHF DPO
24 Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search STRATEGIST：基于双层树搜索的LLM决策自提升方法 reinforcement learning large language model
25 Hologram Reasoning for Solving Algebra Problems with Geometry Diagrams 提出基于全息推理的HGR方法，解决几何图代数问题 reinforcement learning deep reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
26 Dynamic Analysis and Adaptive Discriminator for Fake News Detection 提出动态分析与自适应判别器（DAAD）用于解决虚假新闻检测问题。 manipulation large language model multimodal ✅
27 DisMix: Disentangling Mixtures of Musical Instruments for Source-level Pitch and Timbre Manipulation DisMix：解耦乐器混合音源，实现音高和音色的源级别操控 manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
28 Trajectory Imputation in Multi-Agent Sports with Derivative-Accumulating Self-Ensemble 提出MIDAS，利用导数累积自集成方法解决多智能体运动轨迹插补问题 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页