cs.LG（2024-04-29）

📊 共 11 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Foundations of Multisensory Artificial Intelligence	提出多感知人工智能基础以解决多模态学习问题	large language model foundation model multimodal
2	Unleashing the Power of Multi-Task Learning: A Comprehensive Survey Spanning Traditional, Deep, and Pretrained Foundation Model Eras	综述多任务学习的演变与应用，推动相关领域发展	foundation model	✅
3	M3H: Multimodal Multitask Machine Learning for Healthcare	提出M3H框架以解决医疗多任务学习问题	multimodal
4	Feature importance to explain multimodal prediction models. A clinical use case	提出多模态深度学习模型以预测老年髋关节骨折患者术后死亡率	multimodal
5	LLM-SR: Scientific Equation Discovery via Programming with Large Language Models	提出LLM-SR以解决科学方程发现问题	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
6	DPO Meets PPO: Reinforced Token Optimization for RLHF	提出RTO框架以优化RLHF中的策略学习问题	reinforcement learning deep reinforcement learning PPO	✅
7	Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models	提出AIME-NoB以解决预训练模型在模仿学习中的知识障碍问题	imitation learning world model world models	✅
8	Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs	提出结合RL与LLMs的代理以提升文本教育环境中的泛化能力	reinforcement learning large language model
9	Reduced-Rank Multi-objective Policy Learning and Optimization	提出降秩多目标政策学习方法以优化干预决策	policy learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty	提出一种样本高效的多智能体强化学习方法以应对环境不确定性	sim-to-real reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
11	A Survey on Diffusion Models for Time Series and Spatio-Temporal Data	提出扩散模型以解决时间序列和时空数据生成问题	spatiotemporal	✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页