Michael Gold
5K posts
@michaelgold
Investing in open source physical AI
Got HTML rendering in canvas working AS IS on all browsers, including iOS Safari - html-in-canvas polyfill - interactions - hover, focus, active, typing etc - css animations - scrolling - caret and text selection - #threejs, #webgl, #webgpu support - dark/light mode Link below
Doom on DOM? DOS rendered client-side onto a simulated cloth in a scanned UE5 scene (Gaussian splats). Live HTML, placed directly into 3D. Fully interactive, even on mobile.
Static 3D generation isn't enough. We need assets ready for animation. Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once. Code is fully open-sourced! Kudos to @KyrieIr31012755 and @VastAIResearch 🧵(1/4)
🤯Topology & UV — the NO.1 headaches in #3D GenAI. 🔥We just move closer to BOTH at the same time. Introducing SATO: Strips as Tokens, a new autoregressive model for topology & UV, has been conditionally accepted to #SIGGRAPH 2026. Will available at #Hyper3D More details👇
Got HTML rendering in canvas working AS IS on all browsers, including iOS Safari - html-in-canvas polyfill - interactions - hover, focus, active, typing etc - css animations - scrolling - caret and text selection - #threejs, #webgl, #webgpu support - dark/light mode Link below
Static 3D generation isn't enough. We need assets ready for animation. Our new #SIGGRAPH work, AniGen, takes a single image and generates the 3D shape, skeleton, and skinning weights all at once. Code is fully open-sourced! Kudos to @KyrieIr31012755 and @VastAIResearch 🧵(1/4)
Got HTML rendering in canvas working AS IS on all browsers, including iOS Safari - html-in-canvas polyfill - interactions - hover, focus, active, typing etc - css animations - scrolling - caret and text selection - #threejs, #webgl, #webgpu support - dark/light mode Link below
