A very simple framework for state-of-the-art Natural Language Processing (NLP)

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

xLSTM as Generic Vision Backbone

Kolmogorov Arnold Networks

OCR, layout analysis, reading order, line detection in 90+ languages

LLM training in simple, raw C/CUDA

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.

Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…

A natural language interface for computers

Effortless data labeling with AI support from Segment Anything and other awesome models.

EyeLoop is a Python 3-based eye-tracker tailored specifically to dynamic, closed-loop experiments on consumer-grade hardware.

List of papers about Proteins Design using Deep Learning

Code for running RFdiffusion

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

Official Implementation for CVPR2023 paper "GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning"

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)