Experiments for understanding disentanglement in VAE latent representations

[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.

Fast and accurate automatic speech recognition (ASR) for edge devices

Pure C inference of Mistral Voxtral Realtime 4B speech to text model

Object Detection & Tracking with Object Velocity - Hobby Project

Low-latency AI engine for mobile devices & wearables

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

A Bulletproof Way to Generate Structured JSON from Language Models

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

Modified Swin Transformer model in PyTorch on CIFAR-10 for image classification

✨✨Latest Advances on Multimodal Large Language Models

tiny vision language model

LLM Council works together to answer your hardest questions

An extremely fast Python package and project manager, written in Rust.

Puzzles for learning Triton

Open Hardware Monitor

The best ChatGPT that $100 can buy.

🐍 Geometric Computer Vision Library for Spatial AI

Find why PyTorch training is slow while it’s still running

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets. It helps enhance the quality of both images and labels, while significantly reducing d…

Kimi K2 is the large language model series developed by Moonshot AI team

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Open Source Computer Vision Library

Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.

It is my belief that you, the postgraduate students and job-seekers for whom the book is primarily meant will benefit from reading it; however, it is my hope that even the most experienced research…

Sync entire obsidian library to notion database with images included. Minimal user intervention after initial setup, can be run multiple times without duplicating values to provide a backup like ex…

Linux kernel source tree

Learn AI and LLMs from scratch using free resources

Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.