Augmented Reality (AR/VR): AI News Week Ending 09/04/2026

Every week, I organize 400 to 700 links into roughly 60 categories as part of my ongoing effort to learn about AI. This is my personal notebook, which I enjoy sharing with friends… a hobby and a labor of love, rather than a commercial publication or product.

If you arrived here through a search or shared link, this page collects the links I found for Augmented Reality (AR/VR) for the week ending September 4, 2026.

As part of my learning process, I like to automate the category covers. It gives me a chance to learn Python and APIs.

This week’s cover prompt was written using Claude Opus 4.7, and the image was generated using Nano Banana 2.1.

Category Cover Image Prompt: A psychedelic screen-printed gig poster of a VR headset floating center-frame, its two lenses opening as portals into swirling fractal worlds of autumn forest and geometric desert, kaleidoscopic op-art ripples blooming outward in electric magenta, acid orange, deep teal, and lime green on cream paper, with falling leaves and tiny pumpkins drifting through an ornate border, and the bold hand-lettered words 'AR/VR' arcing above the headset in warped 1960s Fillmore-style title lettering, flat ink layers with slight registration offset and visible paper texture.

This Week in Augmented Reality (AR/VR) News

Summary by Claude Sonnet 5.5 based on this week’s links:

Atlas from World Labs: The week's biggest spatial release was Atlas, which World Labs describes as a multimodal world model that generates frames with precise camera control and reconstructs them in 3D. Ben Mildenhall said he built a flythrough of London's Natural History Museum from just three input images he found online.
Real photos to robot sims: Several researchers pointed to real2sim for robotics. Yunzhu Li showed casual phone photos becoming a simulated environment where robots navigate, and co-founder Justin Johnson predicted training a robot for a new space from about five phone photos.
Interactive worlds and 3D from GPT-6 Astra: Runway announced GWM Worlds 2, which it says generates interactive real-time simulations at 720p and 24 fps. Early-access users of GPT-6 Astra shared 3D houses and scenes built from photos or descriptions, though one noted some details came out wrong.

This summary was generated by Claude Sonnet 5.5 to help you explore the links below. Rest assured, I select, organize, and check the links by hand in Google Sheets, and write the introduction and personal commentary in The Main Newsletters myself each week as a labor of love.

This week's links related to Augmented Reality (AR/VR)

GPT-6 Astra represents a step-function change in model capability for interactive reasoning problems. It scores 66% on ARC-AGI-3 using our standard harness, and nearly 100% with a continuous conversation harness and custom compaction, at a cost of roughly $360 per game. In fact,
https://x.com/fchollet/status/2095598451115614371

Fable 5.1: “Create the Catalog of Ships from the Iliad with a map, etc. i should be able to explore each accurate ship in 3D. there should be real images & archeological data i can draw on. test it with agents to make it accurate & beautiful, then revise
https://x.com/emollick/status/2095352019498447090

God’s Eye View is #1 on GitHub trending this week. A spy satellite simulator in your browser, except the data is real. 16.2k stars, 3.3k forks. 1 in 5 people who starred it forked it, which is pretty cool! Tell your agent to install it, or use the new one-click installer if
https://x.com/bilawalsidhu/status/2095339563971396024

Using voice mode to monitor rush hour traffic in God’s Eye View. It uses aggregated location data from TomTom to visualize how busy every road segment is. And in cities like Austin and London you can look at public CCTV cameras to confirm the actual conditions on the ground.
https://x.com/bilawalsidhu/status/2093333780719337873

@DrJimFan @theworldlabs Indeed Jim, a camera conditioned world model with spatial context has so much horizontal usage including real2sim for robotics!
https://x.com/drfeifei/status/2094910083444707551

@theworldlabs Amazing work! Great step towards real2sim for robotics!
https://x.com/DrJimFan/status/2094905169460736291

NEW WORLD MODEL: @ylecun’s team is back with an efficient model! This project involves @ylecun, @lukaskuhn77, @lucasmaes_, @quentinlldc, and @randall_balestr. A couple definitions first: – DINO: self-DIstillation with NO labels. A self-supervised image model (Meta, 2021) where
https://x.com/LeoKharon/status/2094395060636803122

Another glimpse of Real2Sim with Atlas: capture a real environment with just a number of casual photos from a phone, turn them into a sim, then simulate diverse robots navigating different trajectories. Atlas generates the RGB and depth observations they would see along the way.
https://x.com/YunzhuLiYZ/status/2094926835649790103

Cool update by World Labs; I’m most stoked about doing large scale 3d reconstruction using a sparse set of images. That way you capture what’s most important to get right, and AI fills in the rest of the gaps in the scene.
https://x.com/bilawalsidhu/status/2094853004826452337

Introducing Atlas: The world’s first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D. Model the world, move the camera, and simulate space & time.
https://x.com/theworldlabs/status/2094839756329041984

our new model Atlas also happens to be a capable text-to-image generator, providing it with a strong foundation of “world knowledge”… this generalizes across both single and multi view domains, meaning you can step into even highly stylized scenes with precise 3D control
https://x.com/BenMildenhall/status/2094859820100952575

World Labs co-founder @jcjohnss predicts a real-to-sim-to-real future where Atlas could train a robot for any new environment in minutes using just 5 photos from your phone: “One is this notion of fully in-context learning. Maybe I’ve got a robotics foundation model, then I can
https://x.com/MTSlive/status/2094950206240600308

Today, we’re sharing new research on Solaris, our first Interface World Model. Solaris is a new kind of operating system that generates interactive interfaces frame by frame, in real time, with no code. We find that Solaris outperforms frontier LLMs when generating new
https://x.com/runwayml/status/2094463070466646019

At the limit, world models will become the RL environments for everything. Excited to announce GWM Worlds 2, the first world model with a general action space, merging navigation, manipulation and human interaction in one model. We’re already using it to evaluate
https://x.com/agermanidis/status/2095597719574466676

Atlas is live! A spatial foundation model, trained in-house from scratch. After shipping RTFM last year, I was convinced a single camera-conditioned model could unify most spatial generation tasks. Atlas is that bet at scale. The core idea👇
https://x.com/KeunhongP/status/2094840790061301795

Atlas: A World Model for Spatial Intelligence | World Labs
https://www.worldlabs.ai/blog/atlas

I’m so excited that our @theworldlabs team has achieved a major milestone today! Introducing Atlas – a first of its kind multimodal world model trained from scratch! 🚀 Atlas is capable of generating frames with pixel-perfect camera control, reconstructing large scenes from as
https://x.com/drfeifei/status/2094840371675283673

Runway Research | Introducing GWM Worlds 2
https://runway.com/research/introducing-gwm-worlds-2

Two of us filmed this on a couple phones, and we used Atlas to turn it into a short film. This is just a clip from the @theworldlabs tech blog Atlas is able to generate the parts of the scene that none of the cameras actually filmed. It can freeze time, allowing you to reframe
https://x.com/davidpantera_/status/2094841083805266401

Introducing WeatherNext 3️⃣… our most advanced global weather AI model yet from @GoogleDeepmind and @GoogleResearch With prediction capabilities that are up to 5x sharper than WeatherNext 2, the model generates a forecast with high spatial resolution in order to catch
https://x.com/GoogleAI/status/2095544944190788064

This blows my mind. Turning real world 3d scans with messy topology into procedural 3d scenes (modeled like a human artist would have) has been a tall order. But Astra seems to have cracked it. MSFT flight sim does a basic version of this using 2d satellite imagery and a
https://x.com/bilawalsidhu/status/2095677398192681190

I had an early access to GPT-6 Astra and I can say, everyone in the world now has a 3D designer at their fingertips. I gave it an image of a house and asked to create it in 3D with all the details including toys, appliances and furniture. This a full 3D model reconstruction in
https://x.com/tomkrcha/status/2095598645190291775

I had early access to GPT-6. This model will completely shatter your understanding of what’s possible, and it will start a new era of creativity. It’s hard to explain how big of a jump this is, so I’ll share my tests. 1/6 Made this 3D model and animation in code from an image.
https://x.com/skirano/status/2095595932335170031

GPT-6 Astra is a beast. Give it a Zillow listing. It can 3D model the house based on the listing photos and create a cool promotion video. The video was just created in one shot and there are still some wrong details. But I am sure it will be much better if I ask it to polish
https://x.com/realYunfanYe/status/2095612137582526615

I don’t know if you really understand what these people just did… They built an AI that looks at a few casual real-world videos or photos and instantly turns them into a full 3D playground. You can MOVE THE CAMERA HOWEVER YOU WANT, change the lighting, move objects around,
https://x.com/IlirAliu_/status/2095058646673613045

Atlas is out! What excites me most is the 3D capability, months of work with @bardienus : an AR omni model that beats every specialized model at 3D reconstruction. First clip: fly through the Porsche museum, 500+ frames streamed into a single consistent point cloud; feed-forward
https://x.com/HaoZhang623/status/2094841315783754213

GPT-6 Astra just vibe-coded the Oval Office in 3D. We described the set design > GPT-6 Astra generated the scene code > Higgsfield built the location model in Blender and rendered it with Cycles. The whole pipeline ran end-to-end on Higgsfield Supercomputer.
https://x.com/higgsfield_ai/status/2095630197257367857

God’s Eye View – spy satellite simulator in your browser, but the underlying data is real. Open source. MIT license. 15k stars. Now with a one-click installer on GitHub. Select any tracked object – and see what’s happening around it in near real time. Situational awareness in a
https://x.com/bilawalsidhu/status/2094805327266852868

The future of sports is looking exceedingly bright, esp with all the great work happening in spatial AI. Here’s what Arcturus can pull off with stadium scale capture rigs. Amazing for AR/VR but also the traditional broadcast experience itself.
https://x.com/bilawalsidhu/status/2095259821570232524

Very cool work by Runway. Feels like the best of both worlds — fine grain control of a WYSIWYG editor with the creativity & speed of generative models.
https://x.com/bilawalsidhu/status/2094514322936308043

Agreed – attention IS all you need
https://x.com/bilawalsidhu/status/2095628624145588533

I guess we taking today off homies
https://x.com/bilawalsidhu/status/2095543326791331868

People forget that the “metaverse” is a rather empty place without 3d content. And making 3d content is tedious and expensive. This is why I’m excited about us finally having the means to populate the so called metaverse.
https://x.com/bilawalsidhu/status/2094985357984940161

There’s work arounds to get SAM 3D to work for walking.
https://x.com/8bit_e/status/2094524281212350707

Must-read papers of the week ▪️ From Generation to Simulation: How Far Are World Models from Being True Simulators? ▪️ Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning ▪️ Can Video World Models Track Unobserved World States? ▪️
https://x.com/TheTuringPost/status/2094942136865333544

How soon until an AI agent can organically get a million followers on a video platform like youtube or tiktok – and do so fully autonomously in a couple of months?
https://x.com/bilawalsidhu/status/2094081526459716053

Free viewpoint video with 4x iphones is genuinely nuts. This used to need a volumetric capture rig with dozens if not hundreds of cameras. Offline renders are just the start. Can’t wait till we can playback dynamic 3d content like this in real time.
https://x.com/bilawalsidhu/status/2094912389267284210

We are sharing a major update to our General World Models efforts. GWM Worlds 2 can generate full, interactive, real-time video simulations in one continuous 720p stream at 24 fps and audio at 48000 Hz, responding to your inputs as you explore. It is the first world model that
https://x.com/c_valenzuelab/status/2095548906281042144

God’s Eye View is on GitHub Trending. MIT license. Use voice commands to “jump into the cockpit of the nearest helicopter or jet” or ask “how many military flights are in this region” Turning the 3d globe into a canvas you can annotate w/ voice is really quite fun.
https://x.com/bilawalsidhu/status/2093693183976759387

I’m particularly excited by Atlas’s ability to reconstruct scenes from a very small number of input image — was able to create this flythrough of London’s Natural History Museum by combining 3 input images I found from completely separate sources on Google Images
https://x.com/BenMildenhall/status/2094891871730581609

When @ylecun, @demishassabis, and @drfeifei talk about building world models, what do they mean? → They want AI systems that can build an internal map of their surroundings to anticipate what happens next. But that doesn’t mean they’re building the same machine. @kseniase is
https://x.com/TheTuringPost/status/2094573808006938746

One image. A world to train in, shoot in & explore. 🌍 👀Meet HYPER3D #WorldGen: independent foreground meshes + #3DGS background, built for interaction. For robotics🦾, film🎬, games🎮, DCC💎 & XR. 🔥Powered by our Best Paper Award Project 「CAST」. Let’s Connect the Dots⬇️
https://x.com/DeemosTech/status/2094440163246256523

If you look at the state of the art in procedural 3d generation then you’ll quickly realize that language models will make a serious dent in controllable world building – manifesting whatever we want into existing 3d tools like houdini, blender or unreal.
https://x.com/bilawalsidhu/status/2094219408239440044

This is a creative technologist in the truest sense. Startups and studios can’t hire enough of this person.
https://x.com/bilawalsidhu/status/2094691468111724926

Imagine when this type of just-in-time media generation is connected to something as powerful as tiktok’s for you algorithm. The feed could almost read your mind and materialize videos right before you scroll to them. It would be the most addictive form of media ever created.
https://x.com/bilawalsidhu/status/2093856257165668467

NBS: No Bias Stereo” TL;DR: removes cost volumes, 3D convolutions and iterative refinement from stereo matching, using a simple ViT trained on massive synthetic data to achieve state-of-the-art accuracy with substantially faster inference.
https://x.com/Almorgand/status/2095137213814026302

KISS-GS: 3D Gaussian Splatting Compression Kept Simple” TL;DR: a modular 3DGS compression pipeline combining Gaussian compaction, image-based SOG-XT encoding and optional fine-tuning to achieve 85-319× smaller scenes at matched quality.
https://x.com/Almorgand/status/2094821037678493781

Astra is very good at 3D modeling, and I can’t wait for all of you to experience it, for now here is a little walkthrough on how I built the demo house for our launch blog post. From a Blender scene to a Unreal Engine 5 walkable experience. 🧵
https://x.com/Dimillian/status/2095596700815516004

Woke up today to see God’s Eye View on Product Hunt in the top ten – hunted by the guy who invented the twitter hashtag:
https://t.co/lalxHJ3ABY Meanwhile the open source repository hit number one on GitHub Trending this week and is still number two a few days later. Wild week!
https://x.com/bilawalsidhu/status/2093798887815348521

You are broke, but you wanna do teleop?? How about some open-source, low-cost, 3D-printed leader arm… to teleoperate an SO-ARM? Here you go:
https://t.co/2RUEW7VrHU Tag your favourite open-source project below.👇 And thanks to @LeRobotHF for building this amazing robotics
https://x.com/IlirAliu_/status/2093761096863907947

well this is fucking surreal. god’s eye view is the #1 repo on github trending right now. turns out people want to talk to the planet. loving what people are building and sharing. keep it coming!
https://x.com/bilawalsidhu/status/2093202027631255871

Inverse Rendering for Modeling with Line Primitives” TLDR reconstructs hair, fur, … as explicit line primitives using stochastic diff rasterizer, achieving volumetric-level reconstruction quality while remaining compatible with std rasterization, shading and physics-based sim
https://x.com/Almorgand/status/2095551011775463472

Elastic Triangle Splatting” TL;DR: analyzes triangle-splatting kernels for mesh optimization and novel-view synthesis, introducing an elastic kernel with bilateral gradient support+flexible boundary values that improves geometric reconstruction and perceptual rendering quality.
https://x.com/Almorgand/status/2095179869126549902

World-Grounded Human Motion Recovery via Gravity-View Coordinates” TL;DR: GVHMR estimates human pose in a gravity- and camera-view-defined coordinate system, avoiding autoregressive error accumulation for fast, world-grounded motion recovery from monocular video.
https://x.com/Almorgand/status/2094463178327441627