cs.LG(2023-10-02)

📊 共 17 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) 支柱九:具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱一:机器人控制 (Robot Control) (2 🔗1) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱四:生成式动作 (Generative Motion) (1)

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

#题目一句话要点标签🔗
1 Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP 提出可转移表示学习方法以提升CLIP的零-shot迁移能力 representation learning zero-shot transfer
2 On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused? 揭示开源大语言模型对不当内容生成的脆弱性 reinforcement learning RLHF large language model
3 Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning 提出悲观非线性最小二乘值迭代以解决离线强化学习问题 reinforcement learning offline RL offline reinforcement learning
4 Solving the Quadratic Assignment Problem using Deep Reinforcement Learning 提出深度强化学习方法以解决二次分配问题 reinforcement learning deep reinforcement learning
5 Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity 提出维度依赖适应性以提升多批次强化学习的样本效率 reinforcement learning offline reinforcement learning
6 REMEDI: REinforcement learning-driven adaptive MEtabolism modeling of primary sclerosing cholangitis DIsease progression 提出REMEDI框架以解决原发性硬化性胆管炎的代谢建模问题 reinforcement learning
7 An Investigation of Representation and Allocation Harms in Contrastive Learning 探讨对比学习中的表示与分配损害问题 contrastive learning
8 Linear attention is (maybe) all you need (to understand transformer optimization) 提出线性化Transformer模型以理解优化问题 linear attention

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

#题目一句话要点标签🔗
9 Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers 提出INSTINCT算法以优化大语言模型的指令生成 large language model instruction following chain-of-thought
10 Representation Engineering: A Top-Down Approach to AI Transparency 提出表征工程以提升AI系统透明度 large language model
11 SmartPlay: A Benchmark for LLMs as Intelligent Agents 提出SmartPlay基准以评估大型语言模型作为智能代理的能力 large language model
12 Reconstructing Atmospheric Parameters of Exoplanets Using Deep Learning 提出多目标概率回归方法以重建系外行星大气参数 multimodal
13 Improved Variational Bayesian Phylogenetic Inference using Mixtures 提出VBPI-Mixtures以解决树拓扑后验分布的多模态问题 multimodal

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
14 H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation 提出H-InDex框架以解决灵巧操作中的视觉强化学习问题 manipulation dexterous manipulation reinforcement learning
15 GenSim: Generating Robotic Simulation Tasks via Large Language Models 提出GenSim以解决机器人任务生成的挑战 sim-to-real large language model

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

#题目一句话要点标签🔗
16 Artemis: HE-Aware Training for Efficient Privacy-Preserving Machine Learning 提出Artemis以解决HE-PPML中的高计算成本问题 OMOMO

🔬 支柱四:生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗
17 Nowcasting day-ahead marginal emissions using multi-headed CNNs and deep generative models 提出多头卷积神经网络以实现日内边际排放预测 penetration

⬅️ 返回 cs.LG 首页 · 🏠 返回主页