cs.AI（2024-07-29）

📊 共 14 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 Multimodal Large Language Models for Bioimage Analysis 利用多模态大语言模型进行生物图像分析，加速生物学理解。 large language model multimodal
2 Evaluating Large Language Models for automatic analysis of teacher simulations 评估大型语言模型在教师模拟自动分析中的应用，Llama 3表现更稳定。 large language model
3 ByteCheckpoint: A Unified Checkpointing System for Large Foundation Model Development ByteCheckpoint：为大规模基础模型开发设计的统一检查点系统 foundation model
4 Practical and Reproducible Symbolic Music Generation by Large Language Models with Structural Embeddings 提出基于结构嵌入的大语言模型音乐生成框架，实现可复现的MIDI音乐生成 large language model
5 Leveraging Foundation Models for Zero-Shot IoT Sensing 提出基于基础模型的零样本物联网感知方法以解决未见类别识别问题 foundation model ✅
6 Futga: Towards Fine-grained Music Understanding through Temporally-enhanced Generative Augmentation 提出FUTGA模型，通过时序增强的生成式数据增强实现细粒度音乐理解 large language model ✅
7 Gender, Race, and Intersectional Bias in Resume Screening via Language Model Retrieval 通过语言模型检索揭示简历筛选中的性别、种族和交叉偏见 large language model
8 rLLM: Relational Table Learning with LLMs rLLM：一个基于LLM的关系表学习PyTorch库，支持快速构建RTL模型。 large language model ✅
9 Generative Retrieval with Preference Optimization for E-commerce Search 提出基于偏好优化的生成式检索框架，解决电商搜索中生成式检索的挑战。 large language model
10 Generating Unseen Code Tests In Infinitum 提出自回归基准测试方法，用于持续生成代码测试用例，缓解LLM训练数据泄露问题。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Quantum Machine Learning Architecture Search via Deep Reinforcement Learning 提出基于深度强化学习的量子机器学习架构搜索方法，优化NISQ时代模型性能。 reinforcement learning deep reinforcement learning
12 Imitation Learning for Intra-Day Power Grid Operation through Topology Actions 基于拓扑动作，通过模仿学习提升电网日内运行性能 imitation learning
13 Appraisal-Guided Proximal Policy Optimization: Modeling Psychological Disorders in Dynamic Grid World 提出Appraisal-Guided PPO算法，在动态网格世界中模拟心理障碍行为。 reinforcement learning PPO reward shaping

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
14 Shapley Value Computation in Ontology-Mediated Query Answering 研究本体介导查询应答中Shapley值的计算复杂性，并提出高效算法。 OMOMO

⬅️ 返回 cs.AI 首页 · 🏠 返回主页