Stars
Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
Official electron build of draw.io
Lets make video diffusion practical!
Iterate on LLM-based structured generation forward and backward
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Making a mini version of the BDX droid. https://discord.gg/UtJZsgfQGe
Code for "Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed", CVPR 2024
Efficient and general syntactical decoding for Large Language Models
azooKey is an open-source Japanese keyboard for iPhone and iPad, written in Swift and powered by its own kana-kanji conversion engine. It provides live conversion, flexible key layouts, and a cleanβ¦
ζ₯ζ¬θͺεΉ³ζγη΅ηγ«εγγγ¦ζι©εγγγεΊηε²δΈζγγη―δ»γͺζ©θ½
Official inference framework for 1-bit LLMs
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
This is a repository for all workshop related materials.
Minecraft game engine for massive custom events
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Speech To Speech: an effort for an open-sourced and modular GPT4-o
High-resolution models for human tasks.
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use thβ¦
Media Forensics / Fake Detection experiments in PyTorch. Implements Fighting Fake News: Image Splice Detection via Learned Self-Consistency
Exercises for exploring the Fibertree, Timeloop and Accelergy tools
Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Models, 2023
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.