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 World Models for the week ending August 28, 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 wide 16:9 mid-1980s murder-mystery movie poster of a broad three-story black-and-white engraved Victorian mansion on pure black, with warm amber windows revealing costumed suspects: a cartographer holding a snow-globe city, a smoking-jacketed physicist cradling a frozen billiard ball mid-bounce, and still-life windows crowded with orreries, topographic maps, dioramas and wireframe terrain, plus one window with the shadow of a galloping horse across a rendered landscape; at center the open front door glows warm with the slim silver-haired butler in black tailcoat and white gloves holding a silver tray with a sealed envelope stamped with a tiny gridded globe, fat rounded white title lettering reading 'World Models' arched above the roofline, campy crosshatched engraving style, symmetrical frontal composition.
This Week in World Models News
Summary by Claude Sonnet 5.5 based on this week’s links:
The strongest signal this week came from Chollet, who praised NVIDIA's ARC-AGI-3 work. He noted that, like other high-performing approaches there, it uses deep learning to generate programs on the fly that represent what the system knows about the world.
On the product side, Logan Kilpatrick announced Gemini Omni Flash 1.1, an update to Google's "anything in, anything out" world model. It adds 360p drafts with 4K upsampling, up to 10 seconds of video context when extending, and video extensions in 10-second steps.
A research paper on extrapolative video world models also circulated. Its author said the idea is to learn how the world evolves rather than predict future frames directly, by mapping past frames into latent states and rolling them forward.
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 World Models
This is very nice work from NVIDIA. Like all high-performing approaches on ARC-AGI-3, it uses deep learning-guided on-the-fly synthesis of symbolic world models, i.e. navigating the world by generating programs to represent what you know. To be clear, like with several other”
https://x.com/fchollet/status/2090838046937645398
Excited to bring Gemini Omni Flash 1.1 to the world, this is an update to our anything in, anything out world model. It now supports: – 360p drafts, 4K up samplers – up to 10 seconds of video context when extending – video extensions in 10 second increments – video references”
https://x.com/OfficialLoganK/status/2093014204324417881
Joining the MTS stream today at 10am PST to yap about world models and spatial intelligence!”
https://x.com/bilawalsidhu/status/2090836155906289667
Learning How the World Evolves Extrapolative Video World Models via Latent Dynamics Reasoning paper:
https://x.com/_akhaliq/status/2091958146596041142
Thanks so much for sharing! @_akhaliq 🥰 The core idea is to learn how the world evolves, rather than directly predict what the future looks like. LDR maps past frames into structured latent states and rolls them forward with kinematic integration, learning only the higher-order”
https://x.com/haodongli00/status/2091961954562887884
Leave a Reply