Hugo Vergnes

Somewhere between “nanoGPT toy” and “you need a research lab” there’s a large, under-described region where one person with a few thousand dollars can train a meaningful model.

XMem is a video object segmentation model built around an explicit memory system.

Since I graduated in 2022, the landscape of computer vision has been transformed by the rise of vision transformers (ViTs) and their hierarchical counterparts, which have challenged the dominance of convolutional neural networks (CNNs).

In 2024, my work was accepted for scientific presentation at RSNA 2024!

In recent years, Vision Transformers (ViT) have garnered significant attention for their impressive performance in computer vision tasks.

This project is an exploration of solving Sudoku puzzles using a heuristic approach that mimics human strategies.

Who fought who in UFC lightweight and welterweight match-ups as of 2023.

Graph Neural Networks (GNNs) have shown significant promise in tackling molecular data problems, especially for tasks like drug discovery.