A method to increase the speed and lower the memory footprint of existing vision transformers.
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
Easily configure macOS security settings from the terminal.
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.
Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere
A Solution Accelerator for the RAG pattern running in Azure, using Azure AI Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.
Easily download all the photos/videos from tumblr blogs. 下载指定的 Tumblr 博客中的图片，视频
source code to ICLR'19, 'A Closer Look at Few-shot Classification'
Helpful tools and examples for working with flex-attention
Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.
KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019
