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 14, 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: Photorealistic magazine-cover still life of a single crystal-clear snow globe containing a tiny complete miniature landscape of soft hills, a thin river, and one lone tree, resting on a still mirrored surface with simulated snow fully settled at the bottom, surrounded by vast negative space of pale dawn mist fading to deep cosmic indigo at the edges, soft diffused early light with one delicate thread of warm gold catching the glass, bold clean title text reading World Models placed large in the empty mist above, quiet symmetry, minimalist fine-art composition, crisp detail on the globe while surroundings fall away.
This Week in World Models News
Summary by Claude Sonnet 5.5 based on this week’s links:
- Human video as robot training data: Dyna Robotics introduced Dyna-2, a world-action model pre-trained on more than one million hours of egocentric human video. It learns by predicting both the next video frames and the actions, and the company says it found scaling laws across four orders of magnitude of human data.
- Simulating scenes for robots: Stanford and NVIDIA's PointWorld-1B is a large 3D world model that predicts how a whole scene will move, given RGB-D input and robot actions. It points to world models being used to forecast physical outcomes before a robot acts.
- Memory and open video models: NVIDIA's WorldTrace work on addressable memory for video world models also made a weekly must-read papers list. Separately, LTX released LTX-2.5, pitched as an open world model for video, real-time use, and physical AI.
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
Databricks Grows >80% YoY, Surpasses $7B Revenue Run-Rate, Scales Lakebase, Genie, and Unity AI Gateway – Databricks
https://www.databricks.com/company/newsroom/press-releases/databricks-grows-80-yoy-surpasses-7b-revenue-run-rate-scales
What if a robot could simulate the physical world from a single image. [📍Bookmark Paper & GitHub for later] PointWorld-1B from Stanford and NVIDIA is a large 3D world model that predicts how an entire scene will move, given RGB-D input and robot actions. The key idea is”
https://x.com/IlirAliu_/status/2086151375084265842
WorldTrace: Addressable Memory for Video World Models
https://research.nvidia.com/labs/sil/projects/WorldTrace/
Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws: • world-action models exhibit scaling law on human data across four orders of magnitude, from 1000″
https://x.com/DynaRobotics/status/2086856327150858298
world models are brutal”
https://x.com/dreamingtulpa/status/2086546779852378356
Must-read papers of the week ▪️ EnvACE ▪️ The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows ▪️ SFT Conflicts, RL Coexists ▪️ Addressable Memory for Video World Models ▪️ The Personalization Mirage: How LLMs Fabricate User Profiles,”
https://x.com/TheTuringPost/status/2087141521493787031
Introducing LTX-2.5: The Open World Model for Video, Real-Time, & Physical AI | LTX
https://ltx.io/newsroom/introducing-ltx-2-5
Dyna-2: A 1-Million-Hour Scaling Law for World-Action Models … DYNA
https://www.dyna.co/dyna-2
How well do egocentric human videos scale? Apparently, really well. Dyna Robotics has introduced Dyna-2, a world-action model (WAM) pre-trained on more than 1 million hours of real egocentric human video. It learns by jointly predicting the next video frames and the actions, and”
https://x.com/TheHumanoidHub/status/2086875827296436394
Leave a Reply