cs.LG（2024-02-27）

📊 共 23 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗3) 支柱一：机器人控制 (Robot Control) (2 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Prediction-Powered Ranking of Large Language Models 提出统计框架以改进大型语言模型的排名预测 large language model
2 Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models 提出增强基础模型在上下文学习中的可靠性以解决多种问题 foundation model
3 DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation 提出DropBP以降低大语言模型微调的计算成本 large language model ✅
4 DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning 提出DS-Agent以自动化数据科学任务 large language model ✅
5 Material Microstructure Design Using VAE-Regression with Multimodal Prior 提出基于VAE回归的材料微观结构设计方法以解决结构-性质关联问题 multimodal
6 Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond 提出基于聚类的敏感性采样以解决数据选择问题 foundation model
7 Automated Statistical Model Discovery with Language Models 提出基于语言模型的自动统计模型发现方法 large language model
8 Gradient-based Discrete Sampling with Automatic Cyclical Scheduling 提出自动周期调度以解决高维离散分布采样问题 multimodal
9 Variational Learning is Effective for Large Deep Networks 提出改进变分在线牛顿法以提升大规模神经网络训练效果 large language model
10 Hyperdimensional computing: a fast, robust and interpretable paradigm for biological data 提出超维计算以解决生物数据分析中的效率与可解释性问题 multimodal
11 Prioritizing Informative Features and Examples for Deep Learning from Noisy Data 提出优先考虑信息特征与示例的方法以应对噪声数据问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
12 Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition 提出MultiDAG+CL以解决多模态情感识别中的数据不平衡问题 curriculum learning multimodal ✅
13 Multi-Agent Deep Reinforcement Learning for Distributed Satellite Routing 提出多智能体深度强化学习以解决低地球轨道卫星路由问题 reinforcement learning deep reinforcement learning DRL
14 Beacon, a lightweight deep reinforcement learning benchmark library for flow control 提出Beacon以解决深度强化学习流控基准缺失问题 reinforcement learning deep reinforcement learning ✅
15 Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning 提出时序逻辑规范条件决策变换器以解决离线安全强化学习问题 reinforcement learning decision transformer
16 Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings 提出功能奖励编码以解决无监督零-shot强化学习问题 reinforcement learning offline RL generalist agent ✅
17 Sinkhorn Distance Minimization for Knowledge Distillation 提出Sinkhorn知识蒸馏以解决现有蒸馏方法的不足 teacher-student distillation large language model
18 Intensive Care as One Big Sequence Modeling Problem 提出医疗序列建模范式以提升健康护理决策能力 reinforcement learning large language model foundation model
19 When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback 提出人类反馈下部分可观测性挑战的解决方案 reinforcement learning RLHF
20 LocalGCL: Local-aware Contrastive Learning for Graphs 提出LocalGCL以解决图数据局部结构忽视问题 representation learning contrastive learning
21 Representation learning in multiplex graphs: Where and how to fuse information? 提出多层次信息融合方法以解决多重图节点表示学习问题 representation learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
22 RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences 提出RIME以解决偏好强化学习中的噪声反馈问题 locomotion manipulation reinforcement learning ✅
23 syren-halofit: A fast, interpretable, high-precision formula for the $Λ$CDM nonlinear matter power spectrum 提出syren-halofit以快速准确计算非线性物质功率谱 MPC

⬅️ 返回 cs.LG 首页 · 🏠 返回主页