Spatial Digest
The technologies transforming how we document reality—for journalists, investigators, and historians
As much as spatial technologies offer a promising future of immersive, informative experiences, they also blur lines between reality and simulation, posing risks to trust in records used in documentary filmmaking, as well as journalism, law, history, and other human rights fields that require verifiable ground truth.
Voices
Fred Grinstien
Executive Producer & Content Strategist, Los Angeles, U.S.A.
🔗 Linkedin
Bilawal Siduh
Creative Technologist, Texas, U.S.A.
🔗 Linkedin
Ashley Crowder
Co-founder VNTANA, Los Angeles, U.S.A.
🔗 Linkedin
Michael Rubloff
Founder of RadianceFields.com, New York, U.S.A.
🔗 Linkedin
Hidenori Watanave
University of Tokyo Professor, Tokyo, Japan
🔗 Linkedin
Piotr Sokólski
CTO & Co-Founder, Third Dimension AI
🔗 Linkedin
Spatial Pulse
New and noteworthy developments from around the field
I thought Genie 3 was cool, but not yet useful. Just a week later and now we get to see it's real world potential! @Waymo released their first world model built on top of @GoogleDeepMind 's Genie 3!
— Jonathan Stephens (@jonstephens85) February 6, 2026
The model can take real dashcam footage and expand it into interactive… pic.twitter.com/AMeQFS9Tgo
📢 3D world models from video diffusion suffer from inconsistent frames -> blurry output.
— Matthias Niessner (@MattNiessner) March 18, 2026
Our fix: instead of naïve 3D reconstruction, we non-rigidly align each frame into a globally-consistent 3DGS representation.
->sharp visuals on top of any VDM!https://t.co/laBngKn1wl pic.twitter.com/mcoJ5oqglf
What if a world model could render not an imagined place, but the actual city?
— Junyoung Seo (@jyseo_cv) March 17, 2026
We introduce Seoul World Model, the first world simulation model grounded in a real-world metropolis.
TL;DR: We made a world model RAG over millions of street-views.
proj: https://t.co/Bx4KUAqrRs pic.twitter.com/f5KhV6qSxJ
JEPA are finally easy to train end-to-end without any tricks!
— Lucas Maes (@lucasmaes_) March 23, 2026
Excited to introduce LeWorldModel: a stable, end-to-end JEPA that learns world models directly from pixels, no heuristics.
15M params, 1 GPU, and full planning <1 second.
📑: https://t.co/cpTzgvbTS0 pic.twitter.com/Z2De9ASzcW
World Labs has raised $1 billion in new funding. We are grateful and excited to partner with our investors, including AMD, Autodesk, Emerson Collective, Fidelity Management & Research Company, NVIDIA, and Sea, among others.https://t.co/MfK7mLGKPH
— World Labs (@theworldlabs) February 18, 2026
What representation enables open-world robot manipulation from generated videos?
— Wenlong Huang (@wenlong_huang) March 20, 2026
Introducing Dream2Flow, our recent work that bridges video generation and robot control with 3D object flow.https://t.co/CGJ7h9T0Mb@Stanford #ICRA2026
1/N pic.twitter.com/IVyq5CHquY
Last August, we previewed Genie 3: a general-purpose world model that turns a single text prompt into a dynamic, interactive environment. Since then, trusted testers have taken it further than we ever imagined — experimenting, exploring, and pioneering entirely new interactive… pic.twitter.com/JGsvs7txvf
— Google AI (@GoogleAI) January 29, 2026
⚡️Training RL on world models used to be a headache. Not anymore. ⚡️
— Tengfei Wang (@DylanTFWang) February 10, 2026
Meet *WorldCompass*, a major update to *HY World 1.5*:
🏃♂️ Fast rollouts
🏗️ stable train
✨ Higher quality
paper: https://t.co/GoXEbLVx96
code: https://t.co/cE3QDsj0ec
page: https://t.co/7NPDvkAqG0 pic.twitter.com/P4OKuV2iPR
I am very happy to share the result of my internship at FAIR (Meta): V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning with @ylecun @AdrienBardes
— Loren (@murloren) March 20, 2026
Our approach learns dense, spatially coherent features from video while preserving strong global understanding pic.twitter.com/NVh5CZAGfZ
World Modeling research needs fast iteration, reproducibility, optimized baselines, open-source, and precise zero-shot stress testing. Here comes stable-worldmodel!
— Randall Balestriero (@randall_balestr) February 24, 2026
Paper: https://t.co/aGmoYOId8U
Code: https://t.co/YN3PS5xxV9
Come stress-test your model/idea!
DINO-WM results ⬇️ pic.twitter.com/M4ELoDMlvY