cs.LG（2024-03-15）

📊 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) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors	提出AD3以解决视觉控制中的同质干扰物识别问题	world model world models
2	Parameter Efficient Reinforcement Learning from Human Feedback	提出参数高效的强化学习方法以降低人类反馈的计算成本	reinforcement learning RLHF
3	Online Policy Learning from Offline Preferences	提出虚拟偏好框架以解决离线偏好学习的泛化问题	reinforcement learning policy learning
4	Towards Adversarially Robust Dataset Distillation by Curvature Regularization	提出通过曲率正则化实现对抗鲁棒的数据集蒸馏	distillation	✅
5	Graph Enhanced Reinforcement Learning for Effective Group Formation in Collaborative Problem Solving	提出图增强强化学习以解决协作问题中的有效组队问题	reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
6	Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study	评估多模态基础模型的零-shot鲁棒性以应对现实挑战	foundation model multimodal
7	Block Verification Accelerates Speculative Decoding	提出区块验证以加速推测解码过程	large language model
8	SocialGenPod: Privacy-Friendly Generative AI Social Web Applications with Decentralised Personal Data Stores	提出SocialGenPod以解决用户数据隐私与可移植性问题	large language model	✅
9	pTNAS: Progressive Neural Architecture Search for Tabular Data	提出pTNAS以解决表格数据神经架构搜索效率问题	foundation model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics	提出QDAC以解决深度强化学习中的多样性与性能问题	locomotion reinforcement learning deep reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
11	How Suboptimal is Training rPPG Models with Videos and Targets from Different Body Sites?	提出使用不同身体部位PPG信号训练rPPG模型以提高准确性	PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页