cs.LG（2024-03-10）

📊 共 8 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Disentangling shared and private latent factors in multimodal Variational Autoencoders	提出改进的多模态变分自编码器以解决模态特异性变异问题	multimodal
2	Nonparametric Automatic Differentiation Variational Inference with Spline Approximation	提出基于样条的非参数自动微分变分推断方法以解决复杂后验近似问题	multimodal
3	A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment	提出一个用于验证在线真值推断算法的数据集	TAMP
4	FrameQuant: Flexible Low-Bit Quantization for Transformers	提出FrameQuant以实现Transformer模型的灵活低位量化	foundation model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
5	Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning	提出$L_0$范数正则化以优化深度强化学习策略	reinforcement learning deep reinforcement learning DRL
6	A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents	提出优化确定性等价的风险敏感强化学习方法	reinforcement learning
7	Distributional Successor Features Enable Zero-Shot Policy Optimization	提出分布式后继特征以解决零-shot策略优化问题	reinforcement learning model-based RL	✅

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

#	题目	一句话要点	标签	🔗	⭐
8	Generalization of Graph Neural Networks through the Lens of Homomorphism	通过同态分析提出GNN泛化能力的新方法	OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页