cs.LG（2024-01-18）
📊 共 14 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (6 🔗1)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities | 评估基础模型在联邦学习中的后门漏洞 | foundation model | ||
| 2 | Spatial-Temporal Large Language Model for Traffic Prediction | 提出空间-时间大型语言模型以解决交通预测问题 | large language model | ✅ | |
| 3 | A Fast, Performant, Secure Distributed Training Framework For Large Language Model | 提出一种安全的分布式训练框架以解决大语言模型的隐私问题 | large language model | ||
| 4 | AutoFT: Learning an Objective for Robust Fine-Tuning | 提出AutoFT以解决鲁棒性微调问题 | foundation model | ||
| 5 | Developing an AI-based Integrated System for Bee Health Evaluation | 提出基于AI的综合系统以评估蜜蜂健康 | multimodal | ||
| 6 | Using LLM such as ChatGPT for Designing and Implementing a RISC Processor: Execution,Challenges and Limitations | 探讨利用大型语言模型设计RISC处理器的可行性与挑战 | large language model | ||
| 7 | Excuse me, sir? Your language model is leaking (information) | 提出一种加密方法以隐藏大语言模型中的秘密信息 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Cooperative Edge Caching Based on Elastic Federated and Multi-Agent Deep Reinforcement Learning in Next-Generation Network | 提出基于弹性联邦与多智能体深度强化学习的协作边缘缓存方案以优化网络成本 | reinforcement learning deep reinforcement learning | ||
| 9 | Exploration and Anti-Exploration with Distributional Random Network Distillation | 提出分布式随机网络蒸馏以解决RND的奖励不一致问题 | reinforcement learning deep reinforcement learning distillation | ✅ | |
| 10 | Harnessing Density Ratios for Online Reinforcement Learning | 提出GLOW算法以解决在线强化学习中的密度比率问题 | reinforcement learning offline RL | ||
| 11 | The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning | 将最优传输理论与多智能体强化学习结合以提升效率 | reinforcement learning | ||
| 12 | Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security | 提出多智能体强化学习以解决海洋操作技术网络安全问题 | reinforcement learning | ||
| 13 | Offline Imitation Learning by Controlling the Effective Planning Horizon | 通过控制有效规划视野提出离线模仿学习新方法 | imitation learning |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 14 | Physics-constrained convolutional neural networks for inverse problems in spatiotemporal partial differential equations | 提出物理约束卷积神经网络解决时空偏微分方程逆问题 | spatiotemporal |