论文阅读¶
约 324 个字 预计阅读时间 2 分钟
- Spanner 论文阅读
- DouZero+:基于对手建模和教练引导学习改进斗地主 AI — 论文在 DouZero 基础上加入对手建模和教练引导学习,以改进斗地主智能体训练。
- MVEB: Self-Supervised Learning with Multi-View Entropy Bottleneck
- Diffusion Policy: 基于扩散模型的机器人策略学习
- 冷启动的信号启示:致敬“The Bitter Lesson”,耐心、观察与信号收集的智慧 — justopit
- 如何复现一篇 SIGGRAPH 论文
- Learn "No" to Say "Yes" Better:视觉语言模型的否定理解
- Coconut:Training Large Language Models to Reason in a Continuous Latent Space
- Scaling Llama 3 Training with Efficient Parallelism Strategies
- Generalized Language Models 技术性综述
- Scaling Llama 3 Training with Efficient Parallelism Strategies
- Generalized Language Models 技术性综述
- 多模态平衡学习 On-the-fly Modulation for Balanced Multimodal Learning 论文阅读总结 — kluster
- LRU-K 论文阅读笔记
- 多任务论文阅读 M3GAT — kluster
- 【论文阅读】非局部神经网络浅读(简介+代码)- SuXiaofei's Blog
- Coaxial 论文笔记 服务器 cpu 上用 cxl type3 设备代替 ddr-dram 的设计 — Exce1sior
- Reward Hacking in Reinforcement Learning
- Foundational Models for 3D Point Clouds A Survey and Outlook — wnc 的咖啡馆
- Towards the Generalization of Contrastive Self-Supervised Learning:对比自监督学习泛化性论文笔记
- 用于决策的世界模型 — - 论文 World Models (2018) & PlaNet (2019) 讲解 — 伊犁纯流莱 — 博客园