Runjia Li

DPhil in Computer Vision, University of Oxford || Clarendon Scholar
@Oxford_VGG @OxfordTVG || Experience with @Snap @AIatMeta

[AK @_akhaliq]

Gamma-World

Generative Multi-Agent World Modeling Beyond Two Players

[Runjia Li @RunjiaLi]

Impressive!!

[Jianyuan @jianyuan_wang]

Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.

[RuiningLi @RayLi234]

🚀 Introducing Articraft, a coding agent for articulated 3D asset creation.

Articraft writes code, executes it, receives validation feedback, and refines the result into simulation-ready 3D assets with parts, joints, and motion.

We’re also releasing Articraft-10K: 10,000+ articulated objects across 250 categories, unlocking large-scale interactive scenes for robotics simulation and physical AI.

🔗 Project page: https://t.co/FWutv61yx7
💻 Code: https://t.co/CpCYdBzMlv

[Stan Szymanowicz @StanSzymanowicz]

We made an interactive client-server viewer for LagerNVS with @JonathonLuiten!

You can now interactively explore scenes from just a photo capture - no optimization, no 3D Gaussians, just load your images, run the model on a cloud GPU and stream the renders to your local browser.

Check out the video below for some spaces I recently captured in Oxford, London and beyond!

[Google DeepMind @GoogleDeepMind]

We’re reimagining a 50-year-old interface - the mouse pointer - with AI. 🖱️

These experimental demos show how people can intuitively direct Gemini on their screens using motion, speech, and natural shorthand to get things done 🧵

[Xuanchi Ren @xuanchi13]

We scaled up Lyra to generate explorable 3D worlds! 🚀

Introducing Lyra 2.0 — turning a single image into a 3D world you can walk through, look back, and even drop a robot into 🤖

Code and Model available today!

🌐 Website: https://t.co/plBxCoWkNn

(1/N)

[Alexander Pondaven @alexpondaven]

Introducing ActionParty: the first video world model that controls up to 7 players simultaneously on the same screen across 46 game environments.

We tackle the action binding problem in video diffusion, ensuring each player's action is applied to the right subject. 🧵

[Wei Yu @GnosisYu]

Dropping an exciting new demo of MosaicMem! 👀🔥

A friend brought up a great question:
why not combine long-horizon navigation video generation, promptable world events, and scene concatenation?

Fair point — so we gave it a shot. 🎬✨

For more technical details, check this thread 🧵👇
https://t.co/qyQYwmHsE6

#WorldModel #GenerativeAI #VideoGeneration #InteractiveAI #Genie3 #EmbodiedAI #GameAI

[Runjia Li @RunjiaLi]

@Snapchat The work was done in a joint collaboration with
@WilliMenapace during my internship @Snap.

Many thanks to @moayedhajiali, @ashmrz10, Chaoyang Wang Arpit Sahni, @isskoro, Aliaksandr Siarohin, @JakabTomas, @han_junlin, @SergeyTulyakov, @philiptorr

[Runjia Li @RunjiaLi]

🎉EgoEdit @Snapchat has been accepted to CVPR 2026! 🏆👻

We are bringing high-quality, real-time editing to egocentric videos. Our massive 100k video dataset and benchmark are ALREADY PUBLIC! 🔓🚀

🏠 Project Page: https://t.co/cEUZRxdLDf
🤗 Dataset: https://t.co/qCFRTY8cYG

[AK @_akhaliq]

EgoEdit

Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing

[Runjia Li @RunjiaLi]

@Snapchat Many thanks to coauthors! And thank @_akhaliq for posting our paper!

[AK @_akhaliq]

Mode Seeking meets Mean Seeking for Fast Long Video Generation

paper: https://t.co/TFznQW57cC

[AK @_akhaliq]

WorldWarp

Propagating 3D Geometry with Asynchronous Video Diffusion
https://t.co/7CvB39UGvG

[Junlin Han @han_junlin]

Excited to share our new work: “Learning to See Before Seeing”! 🧠➡️👀 We investigate an interesting phenomeno: how do LLMs, trained only on text, learn about the visual world?
Project page: https://t.co/9mQt3qnckL

[Runjia Li @RunjiaLi]

🎉 VMem is officially accepted to ICCV 2025!
Excited to chat with everyone in Hawaii about making video generation consistent and interactive with our Surfel-Indexed View Memory 🏝️🎥

Also, huge thanks to my insanely helpful coauthors!

[AK @_akhaliq]

VMem

Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

[Tomas Jakab @JakabTomas]

Excited to share VMem: a novel memory mechanism for consistent video scene generation 🎞️✨

VMem evolves its understanding of scene geometry to retrieve the most relevant past frames, enabling long-term consistency

🌐 https://t.co/AHBj6j1ecE
🤗 https://t.co/FbUbJHWW4F

1/ 🧵

[Chuanxia Zheng @ChuanxiaZ]

After two amazing years with @Oxford_VGG, I will be joining @NTUsg as a Nanyang Assistant Professor in Fall 2025!

I’ll be leading the Physical Vision Group (https://t.co/byLxP7FE4a) — and we're hiring for next year!🚀

If you're passionate about vision or AI, get in touch!

[AK @_akhaliq]

VMem

Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

[Zeren Jiang @CodyJzr]

🎁 We present Geo4D, a method that repurposes a video diffusion model for monocular 4D reconstruction.

Project page: https://t.co/BPvlH9tDEP
Code repo: https://t.co/i1pSbsKAQu

𝐌𝐚𝐢𝐧 𝐂𝐨𝐧𝐭𝐫𝐢𝐛𝐮𝐭𝐢𝐨𝐧𝐬:
✨ A novel framework, Geo4D, to reconstruct the dynamic scene, which builds on top of an off-the-shelf video generator.
✨ A multi-modal geometric representation that helps the video diffusion model to learn consistent geometry during training.
✨ A lightweight multi-modal alignment that fuses partially redundant geometric modalities at test time for coherent and robust 4D reconstruction.
✨ Achieved SOTA performance on video depth estimation and comparable performance on camera pose estimation.

Thanks to all co-authors for their invaluable support and contributions.  @ChuanxiaZ, Iro Laina, @dlarlus, Andrea Vedaldi

[Jianyuan @jianyuan_wang]

Introducing VGGT (CVPR'25), a feedforward Transformer that directly infers all key 3D attributes from one, a few, or hundreds of images, in seconds! No expensive optimization needed, yet delivers SOTA results for:

✅ Camera Pose Estimation
✅ Multi-view Depth Estimation
✅ Dense Point Cloud Reconstruction
✅ Point Tracking

Project Page: https://t.co/Qoc1ipqozq

Code & Weights: https://t.co/1GkCpRATkE