cs.LG（2024-04-18）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	TrajDeleter: Enabling Trajectory Forgetting in Offline Reinforcement Learning Agents	提出TrajDeleter以解决离线强化学习中轨迹遗忘问题	reinforcement learning offline RL offline reinforcement learning
2	From $r$ to $Q^*$: Your Language Model is Secretly a Q-Function	提出DPO算法以解决传统RLHF方法的对齐问题	reinforcement learning RLHF DPO
3	Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning	提出基于多标准贝叶斯优化的自适应催化剂发现方法	representation learning
4	Knowledge-Aware Multi-Intent Contrastive Learning for Multi-Behavior Recommendation	提出知识感知多意图对比学习以解决多行为推荐问题	contrastive learning
5	Actor-Critic Reinforcement Learning with Phased Actor	提出分阶段演员以改善强化学习中的策略梯度估计	reinforcement learning
6	Aligning language models with human preferences	提出多种方法以对齐语言模型与人类偏好	reinforcement learning RLHF

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

#	题目	一句话要点	标签	🔗	⭐
7	Is There No Such Thing as a Bad Question? H4R: HalluciBot For Ratiocination, Rewriting, Ranking, and Routing	提出HalluciBot以解决大语言模型中的幻觉问题	large language model
8	FedEGG: Federated Learning with Explicit Global Guidance	提出FedEGG以解决联邦学习中的收敛性问题	large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
9	Learning a Stable, Safe, Distributed Feedback Controller for a Heterogeneous Platoon of Autonomous Vehicles	提出一种稳定、安全的分布式反馈控制器以解决异构车队问题	model predictive control
10	Physics-integrated generative modeling using attentive planar normalizing flow based variational autoencoder	提出基于注意力平面归一化流的变分自编码器以提升物理集成生成建模的重建质量	locomotion

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

#	题目	一句话要点	标签	🔗	⭐
11	Dynamic Modality and View Selection for Multimodal Emotion Recognition with Missing Modalities	提出动态模态与视图选择以解决多模态情感识别中的缺失模态问题	motion prediction multimodal

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

#	题目	一句话要点	标签	🔗	⭐
12	Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolation	提出PROSE-PDE以解决偏微分方程预测问题	spatiotemporal large language model foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页