YifanXu

MQ-Det. Official PyTorch implementation of "Multi-modal Queried Object Detection in the Wild" (accepted by NeurIPS 2023)

Libra. Simple PyTorch implementation of "Libra: Building Decoupled Vision System on Large Language Models" (accepted by ICML 2024)

Evo-ViT. Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer

ContinualTransformer. Python

open_flamingo. An open-source framework for training large multimodal models

Libra2.