Transformer based on a variant of attention that is linear complexity in respect to sequence length

MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models (CVPR 2024)

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

LAVIS - A One-stop Library for Language-Vision Intelligence

Repository for security-related Python scripts.

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.

Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".

This notebook is designed to plot the attention maps of a vision transformer trained on MNIST digits.

Context aware word vectors

A DAP-compatible JavaScript debugger. Used in VS Code, VS, + more

The semantic similarity algorithm tries to find semantically related entities from ConceptNet, DBpedia, and WordNet

PyTorch code of our KG-SP method for Compositional Zero-Shot Learning

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

[TACL'23] VSR: A probing benchmark for spatial undersranding of vision-language models.

Code for building ConceptNet from raw data.

allRank is a framework for training learning-to-rank neural models based on PyTorch.

Simple implementation of OpenAI CLIP model in PyTorch.

This repo contains the code used in the Learn WebGL series on the Invent Box Youtube channel.

Awesome list for research on CLIP (Contrastive Language-Image Pre-Training).

This repository contains demos I made with the Transformers library by HuggingFace.

Unofficial implementation of Unsupervised Monocular Depth Estimation neural network MonoDepth in PyTorch

A template for University of Maryland dissertations

My written solutions to the problem sets in the book Machine Learning - A Bayesian and Optimisation Perspective by Sergios Theodoridis

A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error ＝ 0.34%.