After the Iran war started the US asked satellite firms to delay (then pause) war zone imagery. Why let adversaries use commercial US assets for targeting? Now Iran has released their own imagery. WaPo geolocated them – exposing the full extent of damage to US military sites.
https://x.com/bilawalsidhu/status/2052227041710219421
Human visual positioning system. In the era of ubiquitous maps, photo is equal to location.
https://x.com/bilawalsidhu/status/2053217307661406540
I love these projects because every city is already publishing itself, often unwittingly. Rodin published every towed car in SF in real time. SF noticed and shut the window in 3.5 hours. So many websites and services we use every day are effectively sensors to read world state.
https://x.com/bilawalsidhu/status/2054351915127857642
Love this. Old school matte paintings are a perfectly good way to augment reality. Much larger field of view than holding up your smartphone too.
https://x.com/bilawalsidhu/status/2053538357733384544
Normalize visualizing music with 3d gaussian splats
https://x.com/bilawalsidhu/status/2053588182109704427
Open source real-time world models legit feel like puppeteering reality itself. Now @reactorworld is putting it in everyone’s hands at sub 50 ms latency — type a prompt, change the scene, and control what unfolds as it generates.
https://x.com/bilawalsidhu/status/2052453815342014753
Synthetic Aperture Radar is cool af — a change detection machine that rips through cloud cover, day or night. And ICEYE knows how to show it.
https://x.com/bilawalsidhu/status/2052929763455504887
Using AI is about to feel like screen sharing with a really smart and attentive genius. Maybe this is the year computer use AI starts feeling magical?
https://x.com/bilawalsidhu/status/2054260705872740583
The lines between code and content are blurring
https://x.com/bilawalsidhu/status/2052189071447900568
Pixal3D Pixel-Aligned 3D Generation from Images
https://x.com/_akhaliq/status/2054120807425511826
Image Generation Quality Mode is now available on the xAI API. This model has already powered the generation of over 300 million images on Grok. It brings higher realism, stronger text rendering, and better creative control for business professionals.
https://x.com/xai/status/2052193877675983031
Krea 2: AI Image Foundation Model & Style Control
https://www.krea.ai/krea-2
[2605.10730] Qwen-Image-2.0 Technical Report
https://arxiv.org/abs/2605.10730
PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinement”” TL;DR: constrains Gaussian Splatting along viewing rays to refine highly detailed depth maps for multi-view stereo reconstruction
https://x.com/Almorgand/status/2052863460791234974
Leave a Reply