cs.LG(2024-02-01)

📊 共 31 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) (16 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (13 🔗2) 支柱一:机器人控制 (Robot Control) (2)

🔬 支柱二:RL算法与架构 (RL & Architecture) (16 篇)

#题目一句话要点标签🔗
1 Vertical Symbolic Regression via Deep Policy Gradient 提出垂直符号回归深度策略梯度方法以解决符号方程发现问题 reinforcement learning deep reinforcement learning
2 FairEHR-CLP: Towards Fairness-Aware Clinical Predictions with Contrastive Learning in Multimodal Electronic Health Records 提出FairEHR-CLP以解决电子健康记录中的公平性问题 predictive model contrastive learning multimodal
3 Dense Reward for Free in Reinforcement Learning from Human Feedback 提出基于人类反馈的密集奖励方法以优化强化学习 reinforcement learning RLHF reward shaping
4 Augmenting Offline Reinforcement Learning with State-only Interactions 提出状态交互增强离线强化学习以解决奖励反馈缺失问题 reinforcement learning offline reinforcement learning
5 Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management 提出MASA框架以解决动态投资组合风险管理问题 reinforcement learning deep reinforcement learning
6 Repeat After Me: Transformers are Better than State Space Models at Copying 提出Transformer模型以解决GSSM在复制任务中的局限性 state space model large language model
7 Self-Supervised Contrastive Pre-Training for Multivariate Point Processes 提出自监督对比预训练方法以解决多变量事件流建模问题 representation learning large language model foundation model
8 Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spaces 提出Graph-Mamba以解决大规模图序列建模问题 Mamba SSM state space model
9 Learning and Calibrating Heterogeneous Bounded Rational Market Behaviour with Multi-Agent Reinforcement Learning 提出一种新方法以解决异质有界理性市场行为建模问题 reinforcement learning policy learning
10 Adaptive Primal-Dual Method for Safe Reinforcement Learning 提出自适应原始对偶方法以解决安全强化学习问题 reinforcement learning PPO
11 ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update 提出O-DICE以解决离线强化学习中的分布校正估计问题 reinforcement learning offline RL offline reinforcement learning
12 Expert Proximity as Surrogate Rewards for Single Demonstration Imitation Learning 提出TDIL方法以解决单一示范模仿学习中的稀疏奖励问题 imitation learning
13 Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning 提出基于网格强化学习的闭合项发现方法以解决PDE问题 reinforcement learning
14 Score-based Causal Representation Learning: Linear and General Transformations 提出基于得分的因果表示学习以解决干预识别问题 representation learning
15 Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach 提出一种基于模型的强化学习方法以解决延迟反馈的控制问题 reinforcement learning
16 AlphaRank: An Artificial Intelligence Approach for Ranking and Selection Problems 提出AlphaRank以解决固定预算排名与选择问题 reinforcement learning deep reinforcement learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗
17 Efficient Non-Parametric Uncertainty Quantification for Black-Box Large Language Models and Decision Planning 提出非参数不确定性量化方法以解决语言模型决策规划中的幻觉问题 large language model
18 DoubleMLDeep: Estimation of Causal Effects with Multimodal Data 提出DoubleMLDeep以解决多模态数据因果效应估计问题 multimodal
19 The Information of Large Language Model Geometry 提出基于熵理论的LLM几何信息分析方法 large language model
20 EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models 提出EE-Tuning以高效调优早退出大型语言模型 large language model
21 SymbolicAI: A framework for logic-based approaches combining generative models and solvers 提出SymbolicAI框架以整合生成模型与求解器 large language model foundation model
22 Approximate Nearest Neighbor Search with Window Filters 提出c-近似窗口搜索以解决标签范围内的邻近搜索问题 TAMP
23 Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI 提出贝叶斯深度学习以应对大规模AI时代的挑战 foundation model
24 Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents 提出Formal-LLM框架以解决LLM生成计划不可控问题 large language model
25 LLMs learn governing principles of dynamical systems, revealing an in-context neural scaling law 提出LLMs学习动力系统的治理原则以实现高效预测 large language model
26 Fast Exact Unlearning for In-Context Learning Data for LLMs 提出高效精确的反学习方法以应对大语言模型数据问题 large language model
27 Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data 提出浅层变换器的上下文学习理论以解决非结构化数据问题 large language model
28 Efficient Exploration for LLMs 提出高效探索方法以提升大型语言模型的人类反馈收集 large language model
29 Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction 提出基于注意力的动态多层图神经网络以解决贷款违约预测问题 TAMP

🔬 支柱一:机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗
30 SLIM: Skill Learning with Multiple Critics 提出SLIM以解决机器人操作中的技能发现问题 manipulation reinforcement learning
31 Control-Theoretic Techniques for Online Adaptation of Deep Neural Networks in Dynamical Systems 提出控制理论技术以解决深度神经网络在线适应问题 sim2real reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页