[ECCV 2024] SMFANet: A Lightweight Self-Modulation Feature Aggregation Network for Efficient Image Super-Resolution

Efficient optimizers

具身智能入门指南 Embodied-AI-Guide

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

LLM from scratch, no pretrained models, no HF transformers

LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

papers about Face Detection; Face Alignment; Face Recognition && Face Identification && Face Verification && Face Representation; Face Reconstruction; Face Tracking; Face Super-Resolution && Face D…

Optimize RandAugment with differentiable operations

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

leaked prompts of GPTs

[CVPR'24] 3D Neural Edge Reconstruction

CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 seconds

A suite of GShade shaders for Final Fantasy XIV

[CVPR2025] HVI: A New Color Space for Low-light Image Enhancement && "You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement"

[I3D 2024] Deblur-GS: 3D Gaussian Splatting from Camera Motion Blurred Images

Pytorch implementation of "LightM-UNet: Mamba Assists in Lightweight UNet for Medical Image Segmentation"

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

Detect and locate lung nodules from CT images with deep learning

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

Industry leading face manipulation platform

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

PyTorch native post-training library

Open-Sora: Democratizing Efficient Video Production for All

You like pytorch? You like micrograd? You love tinygrad! ❤️

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!

Angular penalty loss functions in Pytorch (ArcFace, SphereFace, Additive Margin, CosFace)

Code for our CVPR'2024 paper "GauHuman: Articulated Gaussian Splatting from Monocular Human Videos"