Joined August 2022
- Tweets34
- Following101
- Followers269
- Likes238
Pinned Tweet
Introducing Mundo:
A customized world model that turns photos of a given place into a world you can explore, edit, and interact with.
Yihang Luo retweeted
What if you could step inside a painting? We use Mundo to imagine new viewpoints from a single image of Raphael’s fresco, The School of Athens.
Yihang Luo retweeted
🎥Reshoot a video from a camera that was never there~
Excited to share #Holo4D, accepted to #neurips2026 !
Give it a video and a new camera path: Holo4D lifts the video into 3D tracks and uses them to steer a video model. The camera moves; what happened stays the same. 🧵
Mundo extends scene exploration to 4D with spatial-temporal simulation. Using multi-camera recordings or an image as context, it renders dynamic events from new viewpoints. We can freeze time at a chosen moment and move the camera to inspect the scene from different angles.
How it works?
Given a few context views, a VLM agent builds and programs a 3D proxy world; code controls its state, physics simulates its dynamics, and a video generation model renders the results.
Mundo enables spatiotemporal exploration, precise interactions, and physically grounded simulations—all driven by code.
More broadly, agentic generation could be the next major paradigm for world models and controllable video generation, unlocking parameterized control and physically grounded interactions.
Yihang Luo retweeted
What if you could step inside a van Gogh painting?
We used Mundo to imagine new viewpoints from a single painting.
Take a look at this short demo.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Yihang Luo retweeted
👋 What if you could turn your own environment into a programmable world—one you can explore, edit, and interact with? 🌍
Excited to introduce Mundo, our customized world model that brings this vision to life! Amazing work led by @onelineluo!
Given a few context views, a VLM agent builds and programs a 3D proxy world; code controls its state, physics simulates its dynamics, and a video generation model renders the results.
Mundo enables spatiotemporal exploration, precise interactions, and physically grounded simulations—all driven by code.
More broadly, agentic generation could be the next major paradigm for world models and controllable video generation, unlocking parameterized control and physically grounded interactions. 🚀
🌍 Introducing Mundo, led by my student @onelineluo: a customized world model that turns images of a place into an environment for exploration, editing, and simulation.
Explore new viewpoints, change objects and physical properties, or simulate robot navigation and manipulation — all within the captured environment.
The key is an explicit, editable world state: code specifies actions, physics computes their consequences, and a video model renders the outcome using the input images as visual context.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Code coming soon!
Yihang Luo retweeted
We’ve built a customizable world model that turns just a few photos into an interactive virtual environment.
Let's transform real-world scenes directly into virtual spaces ready for exploration and manipulation!
Project: mundo-world-model.github.io
Blog: huggingface.co/blog/Luo-Yiha…
Yihang Luo retweeted
🌍 Introducing Mundo, led by my student @onelineluo: a customized world model that turns images of a place into an environment for exploration, editing, and simulation.
Explore new viewpoints, change objects and physical properties, or simulate robot navigation and manipulation — all within the captured environment.
The key is an explicit, editable world state: code specifies actions, physics computes their consequences, and a video model renders the outcome using the input images as visual context.
Project: mundo-world-model.github.io/
Blog: huggingface.co/blog/Luo-Yiha…
Code coming soon!
Gonna be presenting our work, 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere, at #ICML2026!
📍 Hall A, Poster #4017
🕝 Wednesday, July 8 · 2:30–4:15 PM (KST)
Come by to see the work and chat about 3D/4D spatial intelligence!
4RC introduces a unified, fully feed-forward framework for monocular 4D reconstruction that encodes an entire video once and then flexibly queries dense 3D geometry and motion for any frame at any timestamp.
By factorizing scene structure into base geometry and time-dependent displacements, it achieves accurate, efficient, and state-of-the-art performance across diverse 4D reconstruction tasks.
Paper: arxiv.org/pdf/2602.10094
Project Page: yihangluo.com/projects/4RC/
Yihang Luo retweeted
This is why I refuse to work on camera estimation problems. For embodied AI, I consider it a **solved** problem at large – there are better things to spend your time on.
It's only a "problem" in academia.
Yihang Luo retweeted
Introducing 𝗦𝗧𝗿𝗲𝗮𝗺𝟯𝗥, a new 3D geometric foundation model for efficient 3D reconstruction from streaming input. Similar to LLMs, STream3R uses casual attention during training and KVCache at inference.
No need to worry about post-alignment or reconstructing from scratch. You can easily add new frames and update the reconstruction incrementally. Great work by Yushi @GROS17121524 and Yihang @TheYihangLuo !
Project: nirvanalan.github.io/project…
arXiv: arxiv.org/abs/2508.10893
Code: github.com/NIRVANALAN/STream…
See a streaming reconstruction of our S-Lab lobby below!
🔥Streaming-based 3D/4D Foundation Model🔥
We present STream3R, which reformulates dense 3D/4D reconstruction into a sequential registration task with **causal attention**.
- Projects: nirvanalan.github.io/project…
- Code: github.com/NIRVANALAN/STream…
- Model: huggingface.co/yslan/STream3…