cs.LG(2023-10-12)

📊 共 22 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (12 🔗2) 支柱九:具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱五:交互与反应 (Interaction & Reaction) (1) 支柱三:空间感知与语义 (Perception & Semantics) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (12 篇)

#题目一句话要点标签🔗
1 Interpreting Learned Feedback Patterns in Large Language Models 提出学习反馈模式以提高大语言模型的反馈一致性 reinforcement learning RLHF large language model
2 Beyond Traditional DoE: Deep Reinforcement Learning for Optimizing Experiments in Model Identification of Battery Dynamics 提出基于深度强化学习的实验优化方法以解决电池动态建模问题 reinforcement learning deep reinforcement learning
3 Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias 提出离线重训练方法以缓解在线强化学习中的探索偏差问题 reinforcement learning policy learning offline RL
4 Virtual Augmented Reality for Atari Reinforcement Learning 提出虚拟增强现实方法以提升Atari强化学习代理性能 reinforcement learning foundation model
5 Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining 提出理论框架以提升变换器在上下文强化学习中的决策能力 reinforcement learning offline reinforcement learning distillation
6 Reinforcement Learning of Display Transfer Robots in Glass Flow Control Systems: A Physical Simulation-Based Approach 提出深度强化学习方法以优化玻璃流控制系统调度 reinforcement learning deep reinforcement learning
7 Robustness to Multi-Modal Environment Uncertainty in MARL using Curriculum Learning 提出基于课程学习的MARL方法以应对多模态环境不确定性问题 reinforcement learning curriculum learning
8 MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning 提出MetaBox以解决Meta-黑箱优化基准缺失问题 reinforcement learning DRL
9 Splicing Up Your Predictions with RNA Contrastive Learning 提出对比学习方法以提升RNA序列预测精度 contrastive learning
10 Cross-Episodic Curriculum for Transformer Agents 提出跨情节课程算法以提升Transformer代理的学习效率 reinforcement learning imitation learning
11 Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach 提出离线模型基于深度Q学习的联合波束成形优化方法 reinforcement learning deep reinforcement learning
12 A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors 提出对深度贝叶斯神经网络后验分布的对称性探索 world model world models

🔬 支柱九:具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗
13 Jailbreaking Black Box Large Language Models in Twenty Queries 提出PAIR算法以高效识别大型语言模型的安全漏洞 large language model
14 Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting 提出Lag-Llama以解决时间序列预测模型不足问题 foundation model
15 Search-Adaptor: Embedding Customization for Information Retrieval 提出Search-Adaptor以提升信息检索的嵌入定制能力 large language model multimodal
16 Tokenizer Choice For LLM Training: Negligible or Crucial? 研究标记器选择对大语言模型训练的影响 large language model
17 A Recent Survey of Heterogeneous Transfer Learning 综述异构迁移学习方法以解决领域间差异问题 multimodal
18 Towards Robust Multi-Modal Reasoning via Model Selection 提出M^3框架以解决多模态推理中的模型选择问题 large language model
19 Overview of Physics-Informed Machine Learning Inversion of Geophysical Data 综述物理信息机器学习反演算法以处理地球物理数据 large language model
20 LEMON: Lossless model expansion 提出LEMON以解决深度学习模型扩展效率低下问题 foundation model

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

#题目一句话要点标签🔗
21 AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE 提出AutoFHE以解决CNN在FHE下的安全推理效率问题 OMOMO

🔬 支柱三:空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗
22 Eliciting Model Steering Interactions from Users via Data and Visual Design Probes 通过数据与视觉设计探针引导用户与模型的交互 affordance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页