Back to Tools Directory

DiT4DiT

Python

This is the official code repo for DiT4DiT, a Vision-Action-Model (VAM) framework that combines video generation model with flow-matching-based action prediction for generalizable robotic manipulation.

Categories & Topics

roboticsvision-action-modelvideo-generationaction-prediction
View on GitHub

Repository Stats

423
GitHub Stars
32
Forks
423
Watchers
17
Open Issues
License
MIT License
Repository
Mondo-Robotics/DiT4DiT
Last Updated
Yesterday
August 6, 2026
Top Contributors
TeleeMa
11
View all contributors →

Related Tools

aero-hand-open

864

https://shop.tetheria.ai/

ai-fusion-video

1.3k

【融光】 - 基于 Agent 的全流程AI短剧/漫剧/视频创作平台 - Java 底层 | Agent-based end-to-end AI creation platform for short dramas, motion comics, and videos – built on a Java backend.

Gamma-World

653

Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

giga-world-1

1.1k

A Roadmap to Build World Models for Robot Policy Evaluation

HY-Embodied

843

HY-Embodied: Embodied Foundation Models for Real-World Agents

nanobot

46k

Nanobot is a project designed for automating tasks and processes through the use of small, programmable robots. It provides practical solutions for enhancing efficiency and streamlining workflows in various applications.