Chen Geng

Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs.
It generalizes surprisingly well across a wide range of objects and can even be used to learn robotics manipulation policy!

Project page: yanzhelyu.github.io/chord.

a 🧵: 1/n

Yanzhe (yanzhelyu.github.io) is applying for PhD programs this cycle. He is truly exceptional, and any top program would be fortunate to have him. Don’t miss out!

🧵 15/15

This project is led by our talented summer intern Yanzhe Lyu (yanzhelyu.github.io), in collaboration with
Karthik Dharmarajan, @zhang-yunzhi.bsky.social, Hadi Alzayer, @elliottwu.bsky.social, and @jiajunwu.bsky.social.

🧵 14/n

Project page: yanzhelyu.github.io/chord
Paper: arxiv.org/abs/2601.04194

🧵 13/n

This thread only scratches the surface. 🧊

We have a massive gallery of generated 4D results, comparisons, and interactive demos on our website.

🔎 Explore the full gallery:
yanzhelyu.github.io/chord/#app

🧵 12/n

Ezio is playing with his eagle. 🦅🖐️

This 4D scene demonstrates our model's ability to generate human-animal interactions.

Notice the natural timing and coordination between the two figures.

🧵 11/n

Even the Dark Side has to obey the laws of physics! 🌑

Watch a 4D scene of Darth Vader pushing down on a desk lamp.

Notice the articulation: the lamp folds and compresses naturally under the force of the hand. 💡📉

🧵 10/n

A cat jumping onto a cushion. 🐈🛋️

Notice the realistic physical interaction: Watch how the cushion deforms and reacts to the cat's weight as it lands.

Our pipeline generates these subtle contact dynamics automatically, without complex physical equations defined in simulators!

🧵 9/n

With CHORD, the creative possibilities are endless. 🎨

Users can generate a limitless variety of fun 4D worlds.

🍿 Watch this: A generated 4D scene of Captain America taking a break to pet a dog! 🛡️🐕

🧵 8/n

How does it work?

We employ a robust distillation strategy to learn dynamic motion patterns from large-scale video generative models.

Read more in our paper: yanzhelyu.github.io/chord/static...

🧵 7/n

Explicit 4D representations = Perfect memory for 4D world generation. 🧠

This allows us to generate coherent, minute-long 4D worlds without the physics breaking down.

Witness a full minute-long sequence:
1. Move plate to microwave 🍽️
2. Wait for heating ⏳
3. Retrieve plate ✅

🧵 6/n

By leveraging explicit 3D representations, CHORD generates motion that is physically grounded, not just visually plausible.

This ensures physical consistency, enabling direct transfer to robotic systems. 🦾

🔗 View more examples here: yanzhelyu.github.io/chord/#robot

🧵 5/n

Our pipeline generates spatially consistent 4D scenes, meaning they can be viewed from any angle. 🔄

👇 Explore the interactive viewer yourself: yanzhelyu.github.io/chord/#viewer
🧵 4/n

Crucially, our pipeline operates without any category-specific priors or dynamic structural annotations.

This flexibility allows CHORD to generate a diverse range of complex object interactions.

👇 Watch the example below: A generated 4D world showing a child launching a brick with a seesaw.
🧵: 3/n

GenAI excels at generating static 3D shapes, but 4D World Models demand realistic dynamics. CHORD bridges this gap:

Input: Static 3D objects (zero dynamic annotations). Output: Plausible 4D object motion & coherent 4D scenes.

No rigs or skeletons required.

🧵: 2/n

Introducing CHORD, a universal framework for generating scene-level 4D dynamic motion from any static 3D inputs.
It generalizes surprisingly well across a wide range of objects and can even be used to learn robotics manipulation policy!

Project page: yanzhelyu.github.io/chord.

a 🧵: 1/n