This is your work, valued

YifanXu

Advanced
@YifanXu74

Postdoc at KAUST. Research Interests: World Model, Vision-Language Representation, Computer Vision.

yifanxu74.github.io

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

346

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

146

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

74

ContinualTransformer. Python

2

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

1

Libra2.

1