cs.LG（2024-03-12）

📊 共 18 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Towards Graph Foundation Models for Personalization 提出图基础模型以提升个性化推荐效果 large language model foundation model
2 Duwak: Dual Watermarks in Large Language Models 提出Duwak以提高大语言模型水印的效率与质量 large language model
3 Characterization of Large Language Model Development in the Datacenter 提出故障容忍预训练与解耦调度以优化LLM开发 large language model
4 WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks? 提出WorkArena以评估网络智能体在知识工作任务中的能力 large language model multimodal
5 CHAI: Clustered Head Attention for Efficient LLM Inference 提出聚类头注意力机制以提高大语言模型推理效率 large language model
6 KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction 提出KnowCoder以解决通用信息提取问题 large language model
7 generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation 提出generAItor以解决语言模型输出可解释性与适应性问题 large language model
8 Fast, accurate and lightweight sequential simulation-based inference using Gaussian locally linear mappings 提出基于高斯局部线性映射的快速轻量级推断方法 multimodal
9 CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning 提出CALF框架以解决LLM在时间序列预测中的分布差异问题 large language model ✅

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

#题目一句话要点标签🔗⭐
10 A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective 提出A2PO以解决离线强化学习中的约束冲突问题 reinforcement learning offline reinforcement learning ✅
11 Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation 提出对抗性数据增强方法以解决离线任务表示学习中的策略干扰问题 reinforcement learning representation learning contrastive learning
12 Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning 提出对称Q学习以解决贝尔曼误差偏斜问题 reinforcement learning deep reinforcement learning
13 Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning 通过生成学习提升强化学习的泛化能力 reinforcement learning
14 Constrained Optimal Fuel Consumption of HEV: A Constrained Reinforcement Learning Approach 提出约束强化学习方法以解决混合电动车的燃油消耗优化问题 reinforcement learning
15 Reinforced Sequential Decision-Making for Sepsis Treatment: The POSNEGDM Framework with Mortality Classifier and Transformer 提出POSNEGDM框架以改善脓毒症治疗效果 reinforcement learning decision transformer

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

#题目一句话要点标签🔗⭐
16 Scalable Spatiotemporal Prediction with Bayesian Neural Fields 提出Bayesian Neural Field以解决大规模时空预测问题 spatiotemporal ✅
17 Machine Learning for Soccer Match Result Prediction 利用机器学习预测足球比赛结果的研究进展 spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
18 xMLP: Revolutionizing Private Inference with Exclusive Square Activation 提出xMLP以解决私有推理中的激活函数效率问题 MPC OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页