cs.LG（2024-03-04）

📊 共 10 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

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

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

#	题目	一句话要点	标签	🔗	⭐
1	Enhancing LLM Safety via Constrained Direct Preference Optimization	提出C-DPO以提高大型语言模型的安全性	reinforcement learning RLHF DPO
2	Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning	提出迭代Q网络以提升深度强化学习的样本效率	reinforcement learning deep reinforcement learning
3	Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences	比较人类偏好学习的奖励模型与直接策略优化	reinforcement learning RLHF DPO
4	A Theoretical Analysis of Self-Supervised Learning for Vision Transformers	提出理论分析以揭示自监督学习在视觉变换器中的表现差异	masked autoencoder MAE contrastive learning
5	Towards Fair and Efficient Learning-based Congestion Control	提出Astraea以解决学习型拥塞控制的公平性与效率问题	reinforcement learning deep reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
6	TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models	提出TPLLM框架以解决交通预测数据稀缺问题	spatiotemporal large language model
7	ComS2T: A complementary spatiotemporal learning system for data-adaptive model evolution	提出ComS2T以解决城市数据适应性问题	spatiotemporal

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

#	题目	一句话要点	标签	🔗	⭐
8	Wukong: Towards a Scaling Law for Large-Scale Recommendation	提出Wukong以解决推荐系统中的规模法则问题	large language model
9	Towards Foundation Time Series Model: To Synthesize Or Not To Synthesize?	提出基础时间序列模型以解决多时间序列预测问题	foundation model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Physics-Informed Neural Networks with Skip Connections for Modeling and Control of Gas-Lifted Oil Wells	提出改进的物理信息神经网络以优化气举油井建模与控制	MPC model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页