Year: 2024

https://github.com/TencentARC/BrushEdit

https://github.com/Genesis-Embodied-AI/Genesis

https://genesis-world.readthedocs.io/en/latest

Genesis is a physics platform designed for general purpose Robotics/Embodied AI/Physical AI applications. It is simultaneously multiple things:

1. A universal physics engine re-built from the ground up, capable of simulating a wide range of materials and physical phenomena.
2. A lightweight, ultra-fast, pythonic, and user-friendly robotics simulation platform.
3. A powerful and fast photo-realistic rendering system.
4. A generative data engine that transforms user-prompted natural language description into various modalities of data.

https://snap-research.github.io/wonderland

https://substack.com/inbox/post/153106976

https://techcrunch.com/2024/12/14/what-are-ai-world-models-and-why-do-they-matter/

A model that can generate the next frame of a 3D scene based on the previous frame(s) and user input, trained on video data, and running in real-time.

World models enable AI systems to simulate and reason about their environments, pushing forward autonomous decision-making and real-world problem-solving.

The key insight is that by training on video data, these models learn not just how to generate images, but also:

• the physics of our world (objects fall down, water flows, etc)
• how objects look from different angles (that chair should look the same as you walk around it)
• how things move and interact (a ball bouncing off a wall, a character walking on sand)
• basic spatial understanding (you can’t walk through walls)

Some companies, like World Labs, are taking a hybrid approach: using World Models to generate static 3D representations that can then be rendered using traditional 3D engines (in this case, Gaussian Splatting). This gives you the best of both worlds: the creative power of AI generation with the multiview consistency and performance of traditional rendering.

https://diamond-wm.github.io

https://jalammar.github.io/illustrated-transformer

https://tensor.art