---
title: "Princeton's UniMate Animates Dragons, Crabs and Robots With one AI Model"
subtitle: "A Princeton-led team released UniMate, a single diffusion transformer that animates any rigged skeleton from text, with code, dataset, and interactive demo."
url: "https://alphasignal.ai/news/princeton-s-unimate-animates-dragons-crabs-and-robots-with-one-ai-model"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-10-01T12:02:07.683Z"
updated: "2026-10-01T12:05:21.282Z"
type: "Repo"
topics:
  - "Video"
  - "Data"
subtopics:
  - "Video Generation"
  - "Datasets"
upvotes: 12
source_url: "https://github.com/Friedrich-M/UniMate"
comments: 0
truncated: true
---

# Princeton's UniMate Animates Dragons, Crabs and Robots With one AI Model

> A Princeton-led team released UniMate, a single diffusion transformer that animates any rigged skeleton from text, with code, dataset, and interactive demo.

# UniMate animates different skeletons with one motion model

[UniMate](https://linzhanmou.com/unimate/) generates articulated motion from a rigged 3D asset and a text prompt. A single checkpoint handles humans, dragons, crabs, snakes, octopuses, cheetahs, and mechanical objects without per-skeleton fine-tuning or test-time optimization. Researchers from Princeton, UC Berkeley, MIT, and NTU describe the system in a SIGGRAPH Asia 2026 paper.

At the time of writing, the [GitHub repository](https://github.com/Friedrich-M/UniMate) had passed 900 stars, with hundreds added during the previous week. The dataset, processing tools, browser demo, and model weights are public, while training and inference scripts remain pending.

## The skeleton becomes part of the prompt

Skeleton topology describes how joints connect into a kinematic tree. Rigs can differ in joint count, parent-child relationships, proportions, and rest pose, even when their motions look similar. An auto-rigged creature with an unfamiliar hierarchy can therefore fall outside the templates supported by a category-specific animator.

Many learned animation systems assume a fixed human or animal template, require reference motion, or adapt a model to each new skeleton. UniMate passes the supplied skeleton directly into a topology-aware diffusion transformer, which iteratively refines motion tokens while conditioning on the rig and text.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Friedrich-M/UniMate on GitHub](https://github.com/Friedrich-M/UniMate)
- [UniMate project page](https://linzhanmou.com/unimate/)
- [UniMate on Hugging Face](https://huggingface.co/collections/Linzhan/unimate)