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 August 7, 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 Gemini 3.1 Flash Image Preview.
Category Cover Image Prompt: { "category": "AR/VR", "short_title": "Headset at the Water's Edge", "concept_description": "A single VR headset rests on a smooth river stone at the edge of a glassy tidal creek, its visor turned up toward the stars as if it, too, has stopped trying to simulate anything. The real sky, impossibly detailed, mirrors perfectly in the dark water below, dwarfing the small device and making its lenses look humble, almost reverent. A faint warm glow at the far horizon hints at the city left behind, while reeds and mist frame the quiet threshold between the rendered world and the actual one.", "image_prompt": "A fine-art nocturne painting of a single matte VR headset resting on a river stone at the edge of a mirror-still tidal creek, visor tilted up toward a vast field of stars that reflects perfectly in the dark water, surrounded by muted marsh reeds and thin mist with a faint distant warm glow at the low horizon, deep indigo and silver-white palette, bold clean title AR/VR set across the upper night sky in generous negative space."; }
This Week in Augmented Reality (AR/VR) News
Summary by Claude Sonnet 5.5 based on this week’s links:
- World models took over the feed: Several posts treated world models as the hot topic, with one calling it the summer of world models. DeepMind's Kanishka Rao discussed whether a VLM backbone or a world model is the right path for robotics, and a new CG-World dataset proposes computer-graphics-derived training data instead of just more video.
- Products you can try on in your own space: Decart announced Anywear, pitched as agents letting you interact with products inside your own world before buying. Separately, Bilawal Sidhu argued that real-time video models could remove the biggest blocker for mobile AR, which is producing the 3D content itself.
- 3D capture and reconstruction research: Axolotl3D fills in occluded geometry from images, masks and partial point clouds. Another paper captures cloth wrinkles at 1 mm resolution with a 16-camera rig. VideoNeuMat pulls reusable 3D materials out of generative video models.
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)
when you can figure out precisely where every photo was taken in 3d space, it unlocks some pretty cool possibilities”
https://x.com/bilawalsidhu/status/2084808973442548085
Do you call it 4D printing, if the platform moves as well 🤔 3D printing just got a serious upgrade A new five-axis printer can handle 70° overhangs, no support structures needed. This breaks traditional limitations and opens the door to more complex, curved designs. Perfect”
https://x.com/IlirAliu_/status/2083252134192042331
Who knew PMF for MediaPipe hand tracking would be performance art for social media 🙂 One of the unpredictable things about vibe coding is it breathes new life into tech that’s been around for ages and gives it a new audience. Threejs is another example.”
https://x.com/bilawalsidhu/status/2084440815334481948
1/ We’re entering the era of agentic commerce, and we believe that world models are the missing engine. Instead of browsing static product pages, agents will let you interact with products inside your own world before making decisions. Today, @DecartAI we’re releasing Anywear👇”
https://x.com/AbermanKfir/status/2084816814593478714
Holy, those insanae releases: MiniMax released a 33B video model that generates synchronized stereo audio and runs on one RTX 5090. H3 combines text, images, video and audio references for generation and editing, with clips up to 15 seconds. ComfyUI’s optimized stack is”
https://x.com/kimmonismus/status/2084229681012711598
VLM backbone or World Model? What’s the right kind of training data? Google DeepMind’s Kanishka Rao on how we might land on the recipe that solves robotics in the next 2-3 years.”
https://x.com/TheHumanoidHub/status/2083067365462528413
Must-read papers of the week ▪️ Wonder: Video World Model Done Better ▪️ DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation ▪️ Parallel Decoding Distillation for Fast Image and Video Generation ▪️ GPT-Red: Automated Red Teaming via”
https://x.com/TheTuringPost/status/2084450502503526618
This is really cool work building off our “Interpreting Physics in Video World Models” paper. People may not realize this yet, but unsupervised latent space simulators are a big deal.”
https://x.com/soniajoseph_/status/2084157222892806197
Useful world models need something different from just more video. New CG-World is a large computer-graphics-derived dataset and protocol that proposes a new approach to training data for world models. ▪️ Its idea is that pixels are observations generated by an underlying”
https://x.com/TheTuringPost/status/2083342704281583668
it’s the summer of World Models”
https://x.com/taiuti/status/2084286971774664922
Only if education could be this interactive ❤️🔥 I’ve had a looong wish to build something genuinely useful through vibe coding, and I finally did it. A 3D human anatomy application built with @threejs using GPT 5.6 Sol. It all started with a single design image that I created”
https://x.com/thebuggeddev/status/2083884856531177942
Axolotl3D: a Unified Framework for Faithful 3D Shape Completion” TL;DR: a multimodal 3D completion model that combines images, visibility masks, camera parameters, and partial point clouds to faithfully reconstruct occluded geometry and maintain multi-view consistency.”
https://x.com/Almorgand/status/2083320823629181152
Synchronized robots, tested in 3D, to boost uptime and cut integration errors: This setup uses RobotStudio to simulate dual-robot coordination with precise axis timing and collision checks. Every move is validated in a digital twin before going live. benefits: ✅ Full axis”
https://x.com/IlirAliu_/status/2085273713520308644
High-Fidelity 4D Cloth Capture Pipeline with a Two-Level Pattern” TL;DR: a 16-camera RGB system captures cloth at 1 mm spatial resolution using a two-level marker pattern plus physics-based reconstruction for temporally coherent 4D wrinkles, folds and self-contact.”
https://x.com/Almorgand/status/2084688158621348072
VideoNeuMat: Neural Material Extraction from Generative Video Models” TL;DR: extracts reusable neural 3D materials from generative video models by turning Wan 2.1 into a virtual gonioreflectometer, then reconstructing materials from just 17 generated views.”
https://x.com/Almorgand/status/2085043522651017277
The biggest blocker to scaling mobile AR experiences was making the 3d content itself. Now you can quite literally make the content on the fly using real time video models.”
https://x.com/bilawalsidhu/status/2085020660464603184
Leave a Reply