cs.LG（2024-10-24）

📊 共 17 篇论文 | 🔗 2 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) (6) 支柱一：机器人控制 (Robot Control) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Adversarial Attacks on Large Language Models Using Regularized Relaxation 提出基于正则化松弛的对抗攻击方法，高效提升大语言模型安全性评估。 large language model
2 Research on Key Technologies for Cross-Cloud Federated Training of Large Language Models 提出跨云联邦训练框架，解决大语言模型单云资源瓶颈问题。 large language model
3 LanFL: Differentially Private Federated Learning with Large Language Models using Synthetic Samples LanFL：利用合成样本和差分隐私的联邦学习框架，用于大型语言模型 large language model
4 Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques 综述：利用深度学习和非侵入式模态进行认知衰退检测 foundation model multimodal
5 Context is Key: A Benchmark for Forecasting with Essential Textual Information 提出CiK基准，评估模型在时间序列预测中整合文本上下文信息的能力 foundation model multimodal ✅
6 TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction TesseraQ：通过块重建实现超低比特LLM后训练量化，显著提升性能。 large language model
7 On the Crucial Role of Initialization for Matrix Factorization 提出Nystrom初始化，加速非凸矩阵分解与LoRA微调收敛 foundation model
8 $C^2$: Scalable Auto-Feedback for LLM-based Chart Generation 提出C²框架，通过自动反馈提升LLM生成图表质量并解决数据稀缺问题。 large language model
9 A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs 利用小模型辅助，提升大语言模型预训练效率与质量 large language model
10 KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing KVSharer：通过层间差异性KV缓存共享实现高效推理 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
11 Large Language Models for Financial Aid in Financial Time-series Forecasting 利用大型语言模型解决金融资助中金融时间序列预测难题 predictive model large language model foundation model
12 Bio2Token: All-atom tokenization of any biomolecular structure with Mamba Bio2Token：利用Mamba实现生物分子结构的全原子Token化 Mamba state space model representation learning
13 Reinforcement Learning the Chromatic Symmetric Function 利用强化学习探索单位区间图色对称函数的计数公式 reinforcement learning
14 Indication Finding: a novel use case for representation learning 提出一种基于表征学习的适应症发现方法，用于挖掘药物的新适应症。 representation learning
15 From Efficiency to Equity: Measuring Fairness in Preference Learning 提出基于经济学理论的偏好学习公平性评估框架，提升AI系统对不同用户偏好的公平表征。 preference learning
16 SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance 提出SAMG以解决O2O强化学习中的数据依赖问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 PointPatchRL -- Masked Reconstruction Improves Reinforcement Learning on Point Clouds PointPatchRL：基于掩码重建的Transformer提升点云强化学习性能 manipulation reinforcement learning representation learning ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页