python torch library for polygon / contour to image (mask, distance map) processing and more

Finetune Llama 3.2, Mistral, Phi, Qwen & Gemma LLMs 2-5x faster with 80% less memory

Repo for the Medical Question Generation paper, to be published in AACL clinical workshop 2024

The official Meta Llama 3 GitHub site

The official code for "SegVol: Universal and Interactive Volumetric Medical Image Segmentation".

Minimalist ML framework for Rust

HuggingFace diffusers' pipeline to run ZestGuide

[ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning

[CVPRW22] Official Implementation of T-Food: "Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval". Accepted at CVPR22 's MULA Workshop.

[ICCV23] Official implementation of eP-ALM: Efficient Perceptual Augmentation of Language Models.

[BMVC22] Official Implementation of ViCHA: "Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"

🤖 A PyTorch library of curated Transformer models and their composable components

It is my belief that you, the postgraduate students and job-seekers for whom the book is primarily meant will benefit from reading it; however, it is my hope that even the most experienced research…

NEVIS'22: Benchmarking the next generation of never-ending learners

Code for our EMNLP-2022 paper: "Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA"

terashuf shuffles multi-terabyte text files using limited memory

Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)

A curated list of vision-and-language pre-training (VLP). :-)

OccamNets apply Occam's razor to architecture design to improve bias-resistance (ECCV 2022 Oral)

Implementation for the paper "Reliable Visual Question Answering Abstain Rather Than Answer Incorrectly" (ECCV 2022: https//arxiv.org/abs/2204.13631).

Python task runner : wrap your scripts to make them idempotent and avoid unwanted parallel runs

Fast and memory-efficient exact attention

This plugin displays your tex source in a textarea so plugins like grammarly can check it.

Kind of CDN for rss feed and .torrent files concerned for YGGtorrent

Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

METER: A Multimodal End-to-end TransformER Framework