Embark on a visual voyage of art inspired by black holes

Black holes have long captured the imagination of both scientists and the general public. These exotic objects—once thought ...
GitHub

VAR: a new visual generation method elevates GPT-style models beyond diffusion & Scaling laws observed

🕹️ Try and Play with VAR! We provide a demo website for you to play with VAR models and generate images interactively. Enjoy the fun of visual autoregressive modeling! We provide a demo website for ...

Graphic design trends you need to know for 2026

"For 2026, this matters because audiences expect visuals that react, evolve, and feel alive," Jane continues. "It signals ...
IEEE

MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations

Abstract: Despite significant progress in Vision-Language Pre-training (VLP), current approaches predominantly emphasize feature extraction and cross-modal comprehension, with limited attention to ...
IEEE

Vision-Language Models for Vision Tasks: A Survey

Abstract: Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks (DNNs) training, and they usually train a DNN for each single visual recognition task, leading to ...
GitHub

This is the official implementation of ICLR 2024 paper "VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models".

We find a commonality of various dirty samples is visual-linguistic inconsistency between images and associated labels. To capture the semantic inconsistency between modalities, we propose versatile ...