cs.LG（2024-10-20）

📊 共 14 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) (8 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training 针对小规模多模态训练，探索课程学习在视觉-语言任务中的作用 curriculum learning multimodal
2 Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective 提出联合后训练框架XRIGHT，解决LLM监督微调和偏好学习中的遗忘问题 preference learning RLHF DPO ✅
3 Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching 提出HS3F，通过异构序列特征森林流匹配加速并提升表格数据生成质量。 flow matching
4 Reinforcement Learning for Dynamic Memory Allocation 提出基于强化学习的动态内存分配方法，提升资源管理效率。 reinforcement learning
5 LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space LAC：提出基于可学习增强的图对比学习框架，提升节点表征质量。 contrastive learning
6 UoMo: A Universal Model of Mobile Traffic Forecasting for Wireless Network Optimization 提出FoMo：用于无线网络优化的通用移动流量预测模型 contrastive learning foundation model
7 Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization 通过轨迹似然最大化优化GFlowNets中的反向策略，提升复杂环境下的模式发现能力。 reinforcement learning reward design
8 Contrast All the Time: Learning Time Series Representation from Temporal Consistency CaTT：通过时间一致性学习时间序列表示，提升下游任务性能。 representation learning contrastive learning ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
9 MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models MIRA：一种用于大型语言模型的联邦多任务学习方法 large language model
10 Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models 提出Faster-GCG，高效破解对齐大语言模型的离散优化对抗攻击 large language model
11 EPIC: Efficient Position-Independent Caching for Serving Large Language Models EPIC：高效的位置无关缓存，用于加速大型语言模型的服务。 large language model
12 IPO: Interpretable Prompt Optimization for Vision-Language Models 提出IPO：一种可解释的提示优化方法，用于提升视觉-语言模型的性能和可理解性。 large language model multimodal
13 Neural Normalized Compression Distance and the Disconnect Between Compression and Classification 提出神经归一化压缩距离，揭示压缩与分类之间的脱节现象 large language model

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

#题目一句话要点标签🔗⭐
14 FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation 提出FastSTI，一种快速时空交通数据填补的条件伪数值扩散模型 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页