Official Code for the paper ELMO : Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces (in ICML 2025)

Official Code for the paper Navigating Extremes: Dynamic Sparsity in Large Output Spaces (in NeurIPS 2024)

Dynamic sparse training and pruning algorithms for pytorch

Extremely simple and fast extreme multi-class and multi-label classifiers.

ECML23 paper+code+supplementary

Renee: End-to-end training of extreme classification models

Tools for multi-label classification problems.

Code for our paper CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification

A PyTorch implementation of the paper Thinking Hallucination for Video Captioning.

LightXML: Transformer with dynamic negative sampling for High-Performance Extreme Multi-label Text Classification

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

A PyTorch implementation of state of the art video captioning models from 2015-2019 on MSVD and MSRVTT datasets.

This repository contains codes related to different Reinforcement Learning algorithms and applications.

Official pytorch implementation of the AAAI 2021 paper "Semantic Grouping Network for Video Captioning"

Video classification tools using 3D ResNet

3D ResNets for Action Recognition (CVPR 2018)

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

The repository contains notebooks to extract different type of video features for downstream video captioning, action recognition and video classification tasks.

Machine learning metrics for distributed, scalable PyTorch applications.

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

This repository contains Pytorch implementation of the image captioning model published in the paper Show attend and tell (Xu et al, 2015)

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training