cs.LG(2024-11-30)

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (5) 支柱九:具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱八:物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗
1 Approximate Fiber Product: A Preliminary Algebraic-Geometric Perspective on Multimodal Embedding Alignment 提出近似纤维积以解决多模态嵌入对齐问题 representation learning multimodal
2 Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation 提出FairDTD,通过双教师知识蒸馏实现公平且高效的图神经网络。 representation learning distillation
3 A Unified Data Representation Learning for Non-parametric Two-sample Testing 提出RL-TST框架,用于非参数双样本检验中的统一数据表示学习 representation learning
4 Towards Fault Tolerance in Multi-Agent Reinforcement Learning 提出基于注意力机制和优先级采样的容错多智能体强化学习方法 reinforcement learning
5 Table Integration in Data Lakes Unleashed: Pairwise Integrability Judgment, Integrable Set Discovery, and Multi-Tuple Conflict Resolution 提出数据湖中表集成方法,解决可集成性判断、集合发现和冲突消解问题 contrastive learning large language model

🔬 支柱九:具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗
6 On Foundation Models for Dynamical Systems from Purely Synthetic Data 提出基于纯合成数据的动态系统基础模型,提升泛化性和数据效率 foundation model
7 Rethinking Strategic Mechanism Design In The Age Of Large Language Models: New Directions For Communication Systems 利用大型语言模型革新通信系统中的策略机制设计 large language model
8 TAROT: Targeted Data Selection via Optimal Transport 提出TAROT,通过最优传输实现面向复杂目标域的数据选择。 multimodal
9 Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks 提出基于输入重排序的方法,提升LLM在对称任务上的性能。 large language model

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

#题目一句话要点标签🔗
10 MQFL-FHE: Multimodal Quantum Federated Learning Framework with Fully Homomorphic Encryption 提出MQFL-FHE框架,利用量子计算和多模态学习提升FHE联邦学习的性能。 OMOMO multimodal

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

#题目一句话要点标签🔗
11 The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning 构建大规模物理模拟数据集The Well,促进机器学习在物理系统建模中的应用。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页