cs.LG(2024-01-29)

📊 共 13 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) (9 🔗1) 支柱九:具身大模型 (Embodied Foundation Models) (2 🔗1) 支柱七:动作重定向 (Motion Retargeting) (1) 支柱一:机器人控制 (Robot Control) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗
1 MLEM: Generative and Contrastive Learning as Distinct Modalities for Event Sequences 提出MLEM模型以解决事件序列自监督学习的挑战 contrastive learning multimodal
2 Context-Former: Stitching via Latent Conditioned Sequence Modeling 提出ContextFormer以解决决策变换器的拼接能力不足问题 reinforcement learning offline RL offline reinforcement learning
3 Effective Communication with Dynamic Feature Compression 提出动态特征压缩以解决工业系统远程通信问题 reinforcement learning deep reinforcement learning DRL
4 Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF 提出迭代数据平滑方法以解决RLHF中的奖励过拟合问题 reinforcement learning RLHF
5 GPS: Graph Contrastive Learning via Multi-scale Augmented Views from Adversarial Pooling 提出GPS方法以解决图对比学习中的增强视图生成问题 representation learning contrastive learning
6 PICL: Physics Informed Contrastive Learning for Partial Differential Equations 提出物理信息对比学习以提升偏微分方程求解的泛化能力 contrastive learning
7 Spectral Co-Distillation for Personalized Federated Learning 提出谱共蒸馏方法以解决个性化联邦学习中的数据异质性问题 distillation
8 Supervised Contrastive Learning based Dual-Mixer Model for Remaining Useful Life Prediction 提出双混合模型以解决剩余使用寿命预测问题 contrastive learning
9 Simple Policy Optimization 提出简单策略优化算法以解决现有强化学习效率问题 reinforcement learning PPO

🔬 支柱九:具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗
10 TrackGPT -- A generative pre-trained transformer for cross-domain entity trajectory forecasting 提出TrackGPT以解决跨域实体轨迹预测问题 large language model
11 Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures 提出Learn-VRF以高效解决抽象推理问题 large language model

🔬 支柱七:动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗
12 A Survey on Structure-Preserving Graph Transformers 综述结构保持图变换器以解决图学习中的结构保留问题 structure preservation

🔬 支柱一:机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗
13 Strategic Usage in a Multi-Learner Setting 提出多学习者环境下的战略用户选择模型以优化服务质量 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页