cs.LG（2023-12-28）

📊 共 18 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (11) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
1 Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning? 主动采样减少离线强化学习中的因果混淆 reinforcement learning offline reinforcement learning
2 Generalizable Visual Reinforcement Learning with Segment Anything Model 提出SAM-G框架，利用SAM提升视觉强化学习在未知环境中的泛化能力 reinforcement learning foundation model
3 Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e 提出基于神经PID策略的PPO算法，用于Mu2e实验中的质子束强度控制 reinforcement learning PPO
4 Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity 提出表示复杂性层次以重构强化学习范式 reinforcement learning model-based RL
5 RLPlanner: Reinforcement Learning based Floorplanning for Chiplets with Fast Thermal Analysis RLPlanner：基于强化学习的Chiplet Floorplanning，加速热分析 reinforcement learning MAE
6 Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources 提出一种基于EXP3的对抗算法以解决资源约束下的偏好学习问题 preference learning
7 Resilient Constrained Reinforcement Learning 提出弹性约束强化学习，解决约束条件未知下的强化学习问题 reinforcement learning
8 Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space 提出基于领域不变表征学习的入侵检测方法，提升零日攻击检测能力 representation learning
9 FedSDD: Scalable and Diversity-enhanced Distillation for Model Aggregation in Federated Learning FedSDD：面向联邦学习的可扩展、多样性增强的蒸馏模型聚合方法 distillation
10 Agnostic Interactive Imitation Learning: New Theory and Practical Algorithms 提出Agnostic交互式模仿学习算法MFTPL-P与Bootstrap-Dagger，解决专家策略非策略类问题。 imitation learning
11 Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation 提出层攻击卸载学习，通过层级攻击和知识蒸馏实现快速精确的机器卸载学习。 distillation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
12 Non-Vacuous Generalization Bounds for Large Language Models 为大型语言模型提供非平凡泛化界限，揭示其泛化能力 large language model
13 The LLM Surgeon 提出基于Kronecker因子曲率逼近的大语言模型剪枝方法，实现高效压缩。 large language model
14 Fast Inference of Mixture-of-Experts Language Models with Offloading 提出一种加速MoE语言模型推理的Offloading策略，可在消费级硬件上运行Mixtral-8x7B。 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Gradient-based Planning with World Models 提出基于梯度的世界模型规划方法，提升在复杂环境中的控制性能。 MPC model predictive control world model
16 The Duck's Brain: Training and Inference of Neural Networks in Modern Database Engines 在数据库引擎中训练和推理神经网络：关系代数与SQL实现 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
17 Fast gradient-free activation maximization for neurons in spiking neural networks 提出基于张量分解的无梯度激活最大化方法，用于分析脉冲神经网络神经元选择性。 VQ-VAE

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
18 An Adaptive Framework of Geographical Group-Specific Network on O2O Recommendation 提出GeoGrouse框架，解决O2O推荐中地理区域用户偏好建模的个性化问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页