Abstract: U-shaped encoder-decoder models have excelled in automatic medical image segmentation due to their hierarchical feature learning capabilities, robustness, and upgradability. Purely CNN-based ...

We present HunyuanVideo, a novel open-source video foundation model that exhibits performance in video generation that is comparable to, if not superior to, leading closed-source models. In order to ...

A monthly overview of things you need to know as an architect or aspiring architect. Unlock the full InfoQ experience by logging in! Stay updated with your favorite authors and topics, engage with ...

Abstract: The morphologies of various surface defects on strip steel suffer from oil stain, water drops, steel textures, and erratic illumination. It is still challenging to recognize defect boundary ...

This work presents TinyFusion, a learnable depth pruning method for diffusion transformers. We highlight the following key findings: The script prune_by_learning.py allows users to prune and derive ...