Awesome GitHub RepositoriesMulti-Task Vision Training

MMF is a modular framework for building, training, and evaluating vision-and-language models. It provides a configuration-driven experiment system where model, dataset, and training parameters are defined through composable YAML files, alongside a curated model zoo of pretrained checkpoints for state-of-the-art multimodal architectures. The framework includes a multimodal dataset loader that downloads, processes, and batches vision-and-language data, and a vision-language model trainer supporting distributed training, mixed precision, and checkpoint-based resumption. The framework distinguish

UniAD es un framework de deep learning unificado para conducción autónoma que integra percepción, predicción y planificación en un único modelo end-to-end. Funciona como una arquitectura de red neuronal que mapea datos de sensores crudos directamente a trayectorias de conducción y planes de movimiento. Este proyecto sirve como una implementación de investigación de un enfoque orientado a la planificación que entrena conjuntamente módulos de ocupación, mapeo y seguimiento de objetos. Emplea un framework de percepción multitarea para optimizar el rendimiento general de la conducción. El sistema cubre una amplia superficie de capacidades, incluyendo pipelines de conducción end-to-end, optimización de movimiento vehicular y agregación de características visuales. Coordina diversas tareas de conducción autónoma para refinar todo el proceso de conducción en un solo ciclo de entrenamiento.

OmniGen is a unified image generation model and diffusion framework that processes text, images, and vision tasks through a single system. It functions as a multimodal diffusion framework that treats diverse vision operations as unified image synthesis problems using shared model weights, removing the need for external adapter modules. The system supports subject-driven image generation to preserve the identity of objects from reference photos and allows for multi-reference image synthesis. It also operates as an instruction-based image editor, modifying visual content through natural languag

This project is a research framework and toolkit designed for training large-scale vision transformers and multimodal language models. It provides a comprehensive suite for vision-language pretraining, enabling the development of models that map images and text into shared latent spaces. The framework is distinguished by its capabilities in high-fidelity image generation and multimodal research, utilizing normalizing flows and variational autoencoders to produce images from text prompts or class labels. It supports the development of both generative and contrastive models, allowing for a wide