模型 / 科研

vla from scratch · aghasalim

VLA From Scratch比较了多模式演示和障碍物寻路任务的动作表示。

action-chunkingdiffusion-policyflow-matchingfrom-scratchimitation-learning
发布者存储库 ↗
vla from scratch · aghasalim 资源页面截图
资源截图·抓获 2026-10-08 ·目视审查

概述

VLA From Scratch compares action representations on multimodal demonstrations and obstacle-routing tasks.<br><br>Publisher summary:“Four VLA action representations compared on multimodal demonstrations:bins, regression, diffusion, flow. Regression drives into the obstacle it should route around; flow keeps multimodality…”<br><br>Use its repository to inspect the implementation, documentation and supported workflows. This directory record identifies the maintainer, code license and related resources; it does not claim that the project has been installed or tested on your robot.

项目信息

维护者
aghasalim
主要语言
Python
存储库代码许可证
MIT
模型重量许可证
未记录
数据集许可
未记录
硬件设计许可证
未记录
维护
未存档在最后记录的元数据中
最后观察到的存储库推送
2026-10-02

代码许可不会自动涵盖模型权重、数据集或硬件设计。未记录的许可证详细信息需要与发布者确认。

文档部分

  • vla-from-scratch
  • Scope, stated first
  • The task, and why it has an obstacle
  • Results
  • Sampling error
  • Latency is where flow earns its place

浏览该资源的类别

探索相关集合

视觉-语言-动作模型 ↗