
Research Scientist @GoogleDeepMind
New York City, USA
Joined December 2017
- Tweets315
- Following517
- Followers1.2K
- Likes1.6K
Pinned Tweet
🍺 LagerNVS (CVPR 2026) 🍺
LagerNVS is a generalizable, feed-forward, real-time Novel View Synthesis network which
- performs rendering in real time,
- generalizes to in-the-wild data,
- works with and without known source cameras,
- sets a new state-of-the-art among deterministic methods,
- can be paired with a diffusion decoder for generative extrapolation.
LagerNVS shows that 3D biases are useful for Novel View Synthesis but explicit 3D representations are not required to achieve them. We use 3D biases in (1) architecture design and (2) pre-training:
(1) In NVS with explicit 3D representations (3DGS, NeRF) reconstruction is typically difficult and slow, but rendering is much faster and simpler. We mimic this process in the network design: we use a large (1B params) encoder and a small, lightweight decoder (ViT-B). This allows increasing the network capacity while still achieving real-time rendering.
(2) The encoder, initialized from VGGT, was pre-trained with 3D reconstruction objectives, making the initial features 3D aware.
Both substantially improve performance.
Project page: szymanowiczs.github.io/lager…
Code: github.com/facebookresearch/…
Paper: arxiv.org/abs/2603.20176
Models: huggingface.co/collections/f…
Work done with @jianyuan_wang @MinghaoChen23 Christian Rupprecht and Andrea Vedaldi
Stan Szymanowicz retweeted
Below Neon 3D modeled a photorealistic lab simulation in Antigravity via Blender MCP 🔥
Stan Szymanowicz retweeted
Anyone can create high-quality MuJoCo sim tasks now with Antigravity Robotics Plugin. Here are prompts I used 🚀 Take it for eval, RL, data-gen ... I'd be surprised if I don't see robot GTA next week!
Teaching robots new tasks just got a lot faster. 🤖
With Gemini 4 Hydrogen and the new robotics plugin for Google @Antigravity, you can connect a supported arm, practice in @MuJoCo simulation, and run tasks in the real world using plain conversation.
n y c n y c n y c n y c
we're hiring research interns at GDM NYC!
come spend a summer in NYC with a really fun crew
(Noah Snavely, Zhengqi Li, Sai Bi, Andrew Liu, Linyi Jin, Stan Szymanowicz, Sherwin Bahmani, Philipp Henzler, Amir Hertz, and many more)
DM if interested!
(pic: view from the office)
31
1,507
Stan Szymanowicz retweeted
Carbon made a pelican demo so you don't have to 😅
fun test of long-horizon coding and the new /swarm feature in Google @Antigravity.
Builder and critic subagents ran iterative loops across Blender and Three.js - checking their own renders to build a playable 3D game of a pelican biking around our Mountain View campus.
Two personal updates!
> I defended my PhD from @Oxford_VGG this week 🎉 Many thanks to my examiners @vincesitzmann and Andrew Zisserman for insightful questions and a fantastic discussion, and to my supervisors Andrea Vedaldi and Christian Rupprecht for an amazing 4-year ride together!!
> Two months ago I moved to NYC to join @holynski_'s team at @GoogleDeepMind, working alongside @Jimantha and an absolutely stacked team. Excited for this new chapter!
Poland has acquired a stake in artificial intelligence voice company ElevenLabs, as the country hopes to become a major European AI hub bloomberg.com/news/articles/…
Stan Szymanowicz retweeted
Introducing ABC: open data, training, and infrastructure for robotics.
We release the largest teleop dataset to date, and extensively investigate design decisions, pretraining, and post-training techniques.
@arthurallshire @Cinnabar233 @adamrasb @redstone_hong @davidrmcall
Timely
Just in time: the Best Paper Award in Robot Learning #ICRA2026 uses 3D camera pose to improve policy learning.
Pretty straightforward: robots live in a 3D world.
Image credit: @CSProfKGD
Stan Szymanowicz retweeted
Just in time: the Best Paper Award in Robot Learning #ICRA2026 uses 3D camera pose to improve policy learning.
Pretty straightforward: robots live in a 3D world.
Image credit: @CSProfKGD
Heading to @CVPR today, excited to see friends old and new! Ping me or come say hi if you want to chat about physical AI
I’ll also be presenting LagerNVS on Saturday morning, might even risk a live demo
15
583
Stan Szymanowicz retweeted
📢📢📢 Velox 🚀: Learning Representations of 4D Geometry and Appearance
In our #CVPR2026 paper, we introduce a method for learning a native 4D representation, useful for many downstream tasks, such as video-to-4D, 3D tracking, cloth simulation, and others!
🌐: apple.github.io/ml-velox
📝: arxiv.org/abs/2605.04527
Stan Szymanowicz retweeted
Gemini Omni lets you step into any world you can imagine, bringing text, images, audio, and video directly to life.
🤖 Made with AI
Stan Szymanowicz retweeted
Excited to share what we are building -- Genie experience grounded in real-world street view. Try it out at labs.google/fx/projectgenie
🤖 Made with AI
Project Genie is a @GoogleLabs experiment that lets you simulate dynamic worlds you can navigate in real time with Genie, our general-purpose world model.
Today, we’re connecting Project Genie to nearly 20 years of Street View data from Google Maps — so you can now build interactive spaces based on real-world locations.
Street View imagery in Project Genie is available now for places in the U.S., and will expand to more locales over time.
#GoogleIO
Stan Szymanowicz retweeted
My whole life, I've wanted to be an elephant riding a motorcycle through my hometown.
Now, it's finally possible.
Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info:
blog.google/innovation-and-a…
Real-world models are here! Stoked to share how we're bringing real-world locations to life by integrating Street View into Genie. Try it now at labs.google/fx/projectgenie and read the blog for more info:
blog.google/innovation-and-a…
Stan Szymanowicz retweeted
Introducing VGGT-Ω: scaling feed-forward reconstruction across static and dynamic scenes, and studying whether the learned geometric representations transfer beyond reconstruction.
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!
Project page: szymanowiczs.github.io/lager…
Code and models available on github and huggingface: github.com/facebookresearch/…
Stan Szymanowicz retweeted
Feed-forward 3D reconstruction should not be limited to predicting one Gaussian per pixel.
We introduce TokenGS, which uses learnable tokens to decouple the 3D Gaussian prediction from the image resolution and the number of input views.
#CVPR2026Highlight
[1/6]



















