cs.AI（2024-01-29）

📊 共 17 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) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱五：交互与反应 (Interaction & Reaction) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱一：机器人控制 (Robot Control) (1)

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

#题目一句话要点标签🔗⭐
1 Green Runner: A tool for efficient deep learning component selection 提出Green Runner以解决深度学习模型选择效率问题 large language model
2 Looking for a better fit? An Incremental Learning Multimodal Object Referencing Framework adapting to Individual Drivers 提出IcRegress以解决个体驾驶者的多模态物体引用问题 multimodal ✅
3 Credit Risk Meets Large Language Models: Building a Risk Indicator from Loan Descriptions in P2P Lending 利用BERT生成风险评分以解决P2P借贷中的信息不对称问题 large language model
4 Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization 提出Prompt4Vis以提升自然语言到数据可视化的转换效果 large language model
5 An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors 利用大型语言模型提升安全代码审查效率 large language model chain-of-thought
6 ReGAL: Refactoring Programs to Discover Generalizable Abstractions 提出ReGAL以解决大语言模型抽象能力不足的问题 large language model
7 An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project 探讨大型语言模型在软件工程项目中的应用与认知 large language model
8 LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning 提出LLM4Vuln框架以解耦和增强LLMs的漏洞推理能力 large language model
9 On the generalization of learned constraints for ASP solving in temporal domains 提出动态约束泛化方法以提升ASP求解器在时间领域的性能 TAMP
10 KAUCUS: Knowledge Augmented User Simulators for Training Language Model Assistants 提出KAUCUS框架以解决用户模拟器知识获取不足问题 instruction following

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

#题目一句话要点标签🔗⭐
11 Triple Disentangled Representation Learning for Multimodal Affective Analysis 提出三重解耦表示学习以解决多模态情感分析问题 representation learning multimodal
12 Attention-based Reinforcement Learning for Combinatorial Optimization: Application to Job Shop Scheduling Problem 提出基于注意力的强化学习方法以解决作业车间调度问题 reinforcement learning
13 Zero-shot Imitation Policy via Search in Demonstration Dataset 提出基于搜索的零-shot模仿策略以解决训练成本高的问题 imitation learning foundation model

🔬 支柱五：交互与反应 (Interaction & Reaction) (2 篇)

#题目一句话要点标签🔗⭐
14 HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inference 提出HEQuant以解决同态加密下的通信效率问题 OMOMO
15 Neural Network Training on Encrypted Data with TFHE 提出一种基于全同态加密的神经网络训练方法以保护数据隐私 OMOMO

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
16 3DG: A Framework for Using Generative AI for Handling Sparse Learner Performance Data From Intelligent Tutoring Systems 提出3DG框架以解决智能辅导系统中的稀疏学习数据问题 3DGS

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 Learning to Manipulate under Limited Information 通过神经网络研究有限信息下的投票操控问题 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页