1 Photos and videos
🚀 Introducing Instruct-Particulate, our new model for inferring articulated structures from static 3D meshes, with significantly improved generalization to novel object categories and support for kinematic prompting.
To achieve this, we scaled our training data 40× and redesigned the model to follow kinematic prompts.
The result: diverse, realistic, simulator-compatible articulated 3D assets can now be generated directly from real-world images!
🔗 Project page: instruct-particulate.github.…
🤗 Demo: huggingface.co/spaces/rayli/…
2
14
85
7,414
Runjia Li retweeted
Jun 7
🌙 Open-sourcing Yume -- a programmable, explicit world model on Godot.
You build a game by describing the world as JSON -- the things in it the rules for how they behave -- and one fixed engine runs it.
github.com/kamwoh/yume
4
15
60
259,313
Impressive!!
May 19
Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.
1
85
🚀 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: articraft3d.github.io/
💻 Code: github.com/mattzh72/articraf…
22
108
746
185,951
Runjia Li retweeted
May 15
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!
5
27
175
16,746
Runjia Li retweeted
May 12
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 🧵
461
1,066
8,608
1,659,151
Runjia Li retweeted
Apr 15
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: research.nvidia.com/labs/sil…
(1/N)
29
122
874
1,145,345
Runjia Li retweeted
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. 🧵
6
10
52
9,503
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 🧵👇
x.com/GnosisYu/status/203502…
#WorldModel #GenerativeAI #VideoGeneration #InteractiveAI #Genie3 #EmbodiedAI #GameAI
World models have made impressive progress in video generation, yet they still struggle with a fundamental challenge: memory. In long rollouts, the camera trajectory gradually drifts from the user-specified motion and revisited scenes no longer align with earlier observations. These errors accumulate over time, causing the generated world to steadily lose coherence.
🚀Excited to share our solution MosaicMem 🌍🧠 — our new hybrid spatial memory for video world models.
Project Page: mosaicmem.github.io/mosaicme…
Paper: huggingface.co/papers/2603.1…
21
107
8,604
🎉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: snap-research.github.io/EgoE…
🤗 Dataset: huggingface.co/datasets/ligu…
EgoEdit
Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing
5
8
105
21,815
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
4
368
Mode Seeking meets Mean Seeking for Fast Long Video Generation
paper: huggingface.co/papers/2602.2…
5
18
121
20,368
WorldWarp
Propagating 3D Geometry with Asynchronous Video Diffusion
huggingface.co/papers/2512.1…
6
15
83
13,940
Runjia Li retweeted
1 Oct 2025
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: junlinhan.github.io/projects…
7
26
158
25,851
🎉 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!
VMem
Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
5
7
60
15,063
Runjia Li retweeted
24 Jun 2025
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
🌐 v-mem.github.io
🤗 huggingface.co/spaces/liguan…
1/ 🧵
VMem
Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory
4
11
58
15,792
Runjia Li retweeted
24 Jun 2025
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 (physicalvision.github.io) — and we're hiring for next year!🚀
If you're passionate about vision or AI, get in touch!
24
29
240
43,442