cs.LG（2024-03-05）

📊 共 11 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 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱一：机器人控制 (Robot Control) (2)

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

#	题目	一句话要点	标签	🔗	⭐
1	World Models for Autonomous Driving: An Initial Survey	综述世界模型在自动驾驶中的应用与挑战	world model world models
2	A Zero-Shot Reinforcement Learning Strategy for Autonomous Guidewire Navigation	提出零-shot强化学习策略以解决导丝导航问题	reinforcement learning deep reinforcement learning
3	Pareto-Optimal Estimation and Policy Learning on Short-term and Long-term Treatment Effects	提出帕累托最优估计与政策学习以解决短期与长期治疗效果的权衡问题	policy learning representation learning
4	SplAgger: Split Aggregation for Meta-Reinforcement Learning	提出SplAgger以提升元强化学习中的任务推断效果	reinforcement learning	✅
5	Pooling Image Datasets With Multiple Covariate Shift and Imbalance	提出一种新方法以解决多协变量偏移与不平衡问题	representation learning 3D reconstruction
6	Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking	提出相关代理以解决奖励黑客问题	reinforcement learning RLHF	✅

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

#	题目	一句话要点	标签	🔗	⭐
7	Controllable Prompt Tuning For Balancing Group Distributional Robustness	提出可控提示调优方法以平衡群体分布鲁棒性问题	multimodal
8	MeanCache: User-Centric Semantic Caching for LLM Web Services	提出MeanCache以解决LLM服务中的语义缓存问题	large language model
9	AceMap: Knowledge Discovery through Academic Graph	提出AceMap以解决科学文献管理与知识发现问题	large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Behavior Generation with Latent Actions	提出VQ-BeT以解决复杂行为生成中的多模态预测问题	manipulation diffusion policy multimodal
11	State-Constrained Zero-Sum Differential Games with One-Sided Information	提出一种新方法解决带状态约束的零和微分博弈问题	manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页