cs.LG（2024-03-21）

📊 共 15 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) (6) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱四：生成式动作 (Generative Motion) (1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
1 Rethinking Adversarial Inverse Reinforcement Learning: Policy Imitation, Transferable Reward Recovery and Algebraic Equilibrium Proof 提出PPO-AIRL + SAC框架以解决AIRL中的政策模仿和奖励恢复问题 reinforcement learning PPO SAC
2 Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models 提出棋类语言模型的内在世界模型与潜变量估计方法 world model world models
3 Heuristic Algorithm-based Action Masking Reinforcement Learning (HAAM-RL) with Ensemble Inference Method 提出HAAM-RL以优化汽车喷涂过程中的颜色批次重排序问题 reinforcement learning model-based RL reward shaping
4 Exploring Task Unification in Graph Representation Learning via Generative Approach 提出GA^2E以解决图表示学习中的任务统一问题 representation learning masked autoencoder
5 Contrastive Balancing Representation Learning for Heterogeneous Dose-Response Curves Estimation 提出对比平衡表示学习以解决异质剂量反应曲线估计问题 representation learning
6 Policy Mirror Descent with Lookahead 提出h-PMD算法以提升强化学习中的策略优化效率 reinforcement learning PPO

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

#题目一句话要点标签🔗⭐
7 Exploring the Potential of Large Language Models in Graph Generation 提出LLM4GraphGen以探索大语言模型在图生成中的潜力 large language model chain-of-thought
8 Foundation Models for Time Series Analysis: A Tutorial and Survey 综述基础模型在时间序列分析中的应用与机制 foundation model
9 Trajectory Data Management and Mining: A Survey from Deep Learning to the LLM Era 综述深度学习与大语言模型在轨迹数据管理中的应用与挑战 large language model foundation model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
10 Constrained Reinforcement Learning with Smoothed Log Barrier Function 提出CSAC-LB以解决无预训练的约束强化学习问题 quadruped locomotion reinforcement learning
11 Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization 提出基于可微仿真与优化的任务最优数据驱动代理模型以解决eNMPC问题 model predictive control reinforcement learning differentiable simulation

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
12 Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention 提出SASQuaTCh以解决传统变换器模型的参数复杂性问题 spatiotemporal
13 Recovering Latent Confounders from High-dimensional Proxy Variables 提出Proxy Confounder Factorization框架以解决高维代理变量中的潜在混杂因素问题 spatiotemporal ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Physics-Informed Diffusion Models 提出物理信息扩散模型以解决生成模型的物理约束问题 physics-informed diffusion

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

#题目一句话要点标签🔗⭐
15 HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption 提出HETAL以解决隐私保护下的迁移学习问题 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页