A General Capacity Frontier of Complex Networks

AirLLM 2.8T LLM inference with single 4GB GPU

Apple Silicon (MLX) port of Karpathy's autoresearch — autonomous AI research loops on Mac, no PyTorch required.

Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C infe…

Linux running inside a PDF file via a RISC-V emulator

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Differentiable boundary element simulations for design and optimization of offshore structures

A reproduction of the Deepseek-OCR model including training

Crop Pollination Database

Pytorch implementation of set transformer

Nested Cross-Validation for Bayesian Optimized Linear Regularization

GRD-TRT-BUF-4I: Ground Truth Buffer for Idling

Code for Graph Normalizing Flows.

GRD-TRT-BUF-4I: Ground Truth Buffer for Idling

PlayStation 4 emulator for Windows, Linux, macOS and FreeBSD written in C++

Official inference repo for FLUX.1 models

Rust CLI Chat App

EV-EcoSim: A grid-aware co-simulation platform for the design and optimization of EV Charging Infrastructure. Link to publication: https://doi.org/10.1109/TSG.2023.3339374

The official PyTorch implementation of Google's Gemma models

A sidebar made with react and styled components

Natural Gradient Boosting for Probabilistic Prediction

The agent engineering platform.

A Python package with metrics for Imbalanced Domains

Repository related to the paper Mimicking the halo-galaxy connection using machine learning

The collection of the research works about Automatic Reinforcement Learning in Microsoft Research Asia.

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.