Valentin Liévin

medical-reasoning. Medical reasoning using large language models

biva-pytorch. Official PyTorch BIVA implementation (BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling)

Unet. U-Net Model for Image Segmentation Problems using PyTorch 0.4

char-VAE. Inspired by the neural style algorithm in the computer vision field, we propose a high-level language model with the aim of adapting the linguistic style.

ovis. Official code for the "Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds"

gan-experiments-pytorch. Experiments with GAN, WGAN, WGAN-GP, DC-GAN, cGAN, AC,GAN and pix2pix

booster-pytorch. A lightweight library to ease the training and tracking of deep neural networks with PyTorch. Data structures and paradigms.

Kaggle-Leaf-classification-using-RNNs. A simple example of how to use RNNs for classification

deep-bayes. Bayesian Regression and Classification models with deep features

ToyDatasets. Simple datasets made to speed-up the development of deep learning models using PyTorch

deep-reader-lda. Project developed in the context of the OI-X challenge at DTU, visit the website for more information.

dgm-template. A template for deep generative models

serve-lm. Serve `transformers` language models using `litestar`. Mimicks `openai.create` API.

whisper-transcript. Transcript videos using Whisper and pyannote (speaker identification)