apple-aiml-research

此仓库包含 "FastVLM: Efficient Vision Encoding for Vision Language Models"（CVPR 2025）的官方实现。

Depth Pro：不到一秒的锐利单目度量深度

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

Hypersim：用于全景室内场景理解的真实感合成数据集

This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

CVNets: A library for training computer vision networks

4M：大规模多模态掩码建模。