Santiago Castro

PyTorch code and models for V-JEPA self-supervised learning from video.

Easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.

tensorflow implementation of 'YOLO : Real-Time Object Detection'

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

This project uses reinforcement learning on stock market and agent tries to learn trading. The goal is to check if the agent can learn to read tape. The project is dedicated to hero in life great Jesse Livermore.

WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

[ACL'19] [PyTorch] Multimodal Transformer

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

This is a Torch implementation of ["Deep Residual Learning for Image Recognition",Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun](http://arxiv.org/abs/1512.03385) the winners of the 2015 ILSVRC and COCO challenges.