A Structured Output Benchmark whose 'ground-truth' is actually right

EasyPortrait - Face Parsing and Portrait Segmentation Dataset

[DEIMv2] Real Time Object Detection Meets DINOv3

LINEAE: An enhanced version of high-speed, high-precision line detection using Scalable Transformers. Built with DINOv3.

WIDER-FACE Face Detector Based On YOLOV8

Algorithm to filter noisy signals for high precision and responsiveness.

Training code and dataset cleasing with Sidon

A Terminal UI framework for Zig

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

[ECCV 2026] Official implementation of "ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device". A compact 6.1M-parameter network for zero-shot monocular depth estimation,…

Uplift modeling and causal inference with machine learning algorithms

[ECCV 2026] FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, recognition, parsing, gaze, attributes and anti-spoofing under one API.

A trusty face analysis research platform developed by Tencent Youtu Lab

Face Transformer for Recognition

🔥 [ICCV 2025 Highlight] Official open-source repo for LVFace: Progressive Cluster Optimization for Large Vision Models in Face Recognition

[NeurIPS 2024] TopoFR: A Closer Look at Topology Alignment on Face Recognition

Exa MCP for web search and web crawling!

Inference for the STFT-VAE continuous audio codec (24kHz, 3.125Hz latent)

Code of TIP2021 Paper《SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition》. We provide both MxNet and Pytorch versions.

Official code for CVPR2024 “VideoMAC: Video Masked Autoencoders Meet ConvNets”

LibreYOLO is a MIT licensed open source computer vision library

Python bindings to PDFium, reasonably cross-platform.

Extract structured text from pdfs quickly

Flash Attention 2 implementation for Turing GPUs

SGLang is a high-performance serving framework for large language models and multimodal models.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM