Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

A memory-safe interior point optimizer for nonlinear programming, written in Rust

Fillerbuster: Multi-View Scene Completion for Casual Captures

[CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

ARCHER2 C++ course

Perspective-stable 3D pixel art

starter from "How to Train a GAN?" at NIPS2016

An implementation of Tiny Recursive Models (TRM)

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

Dataset for https://madebyoll.in/posts/game_emulation_via_dnn/

SAM 3D Objects with Multi-view Images

Automatic Sparse Differentiation in JAX.

Code for the ShapeR research paper

A series of lessons, 0 to hero ai coding agent building guide.

Reinforcement Learning environments based on the 1993 game Doom

A toy implementation of a diffusion transformer based "world model" trained on the game of pong or doom.

NLA 2019 course @ Skoltech.

Small generative models built and trained from scratch to run locally in the browser.

CADAM is the open source text-to-CAD web application

Pure Julia OpenVDB parser for scientific visualization. Read sparse volumetric data (clouds, smoke, simulations) with immutable data structures, trilinear sampling, and ray traversal. Designed for …

A workshop that teaches you how to build your own coding agent. Similar to Roo code, Cline, Amp, Cursor, Windsurf or OpenCode.

Kennedy & O'Hagan (2001) Bayesian calibration framework using GPJax