Tejas Kulkarni
@tejasdkulkarni
CEO @CSM_ai. Interested in AGI, Brain and 3D Art. prev - Scientist @GoogleDeepMind. PhD @mitbrainandcog
Bending time (shipping velocity) is the key moat. It compounds fast and feels good.
I prompted this entire grid in the background while watching some YouTube videos. By 2026, building games will be where AI coding is today. Most people in the industry have no idea about the sweeping changes it will bring - but that’s what makes it exciting: bringing deep…
Going from an idea to a game world requires many steps, including 3D asset generation with parts, topology, PBRs, producing animated concept art, and more. CSM Cube bends time to help you achieve the impossible 🚀⏲️
Which AI frontier lab is closest in terms of getting a base multimodal bioLLM with below specs? It has been almost a year since my father suddenly passed away from Glioblastoma. In the background I have been mapping and calibrating what it would take to solve it. Stack: frozen…
x.com/i/article/1801…
In the 5-10 year horizon, an explicit 3D representation will be needed for: - Vibe coding with game engines - CAD / 3D printing (no alt) - Data engine for action-video models For 3D printing, the only other alternative is to have generalizable robot policies to execute object…
The move away from Lean and analytical theorem provers in AI math models is indicative of a general trend - gradually distill the analytical engine into network weights. By analogy, similar things will happen to game engines - first AI world models will augment rendering engines…
Intricate 3D assets with complex parts are now possible with 3D AI - only on CSM Cube.
CSM Cube has been upgraded to support single image-to-parts generation with AI re-topology.🧊⚡ Get up to 30 parts per asset, each with adaptive poly counts. Perfect for fast, high-quality 3D workflows.🎨🚀
CSM aiで久しぶり遊んでみたら普通に良さそうなの出てきた！！！ UEとかで飛ばせそう！！！
We are thrilled to release the next leap in art-grade 3D generative models. Our single-click model pipeline gives unprecedented mesh outputs, with mesh parts-based topology. It is available now for all Cube tiers to start for free. ☑️ Our multi-stage hierarchical AI models…
Stacks of these seem sufficient to predict and generate large parts of computational reality.
Generative 3D graphics making big strides!
We are thrilled to release the next leap in art-grade 3D generative models. Our single-click model pipeline gives unprecedented mesh outputs, with mesh parts-based topology. It is available now for all Cube tiers to start for free. ☑️ Our multi-stage hierarchical AI models…
After the US, Japan ranks next for CSM AI traction. Excited to deepen our ties there and make it even larger 🇯🇵.
アートグレードの3Dジェネレーティブモデルにおける新たな飛躍をリリースできることを大変嬉しく思います。ワンクリックモデルパイプラインは、メッシュパーツベースのトポロジーを備えた、かつてないメッシュ出力を実現します。Cubeの全プランで今すぐ無料でご利用いただけます。 ☑️…
Solving topology was considered to be a discrete problem, reserved for symbolic or Neuro-symbolic methods. But it turns out continuous vectors can mostly capture a complex 3D discrete topological object, with large number of underlying tokens. Also interestingly diffusion turned…
We are thrilled to release the next leap in art-grade 3D generative models. Our single-click model pipeline gives unprecedented mesh outputs, with mesh parts-based topology. It is available now for all Cube tiers to start for free. ☑️ Our multi-stage hierarchical AI models…
One click AI meshes with part-optimized topology! Without parts, topology is not meaningful but we have solved the core problem. Under the hood, there multiple neural networks doing diffusion and long sequence polygon modeling with transformers.
We are thrilled to release the next leap in art-grade 3D generative models. Our single-click model pipeline gives unprecedented mesh outputs, with mesh parts-based topology. It is available now for all Cube tiers to start for free. ☑️ Our multi-stage hierarchical AI models…
A deep learning native game engine will look as follows: - Real-time video diffusion model as the canvas - A 3D memory system to store 3D/4D traces, which the video model will condition on to give arbitrarily complex storylines.
How far can today's AI tools take us in terms of getting (explicit) 3D controllable AI videos? Here's a tool in our web dev app and resulting outputs. I have been waiting to create kids content for my daughter with AI :D