An In-Depth Analysis of VAR (NIPS 2024 Best Paper): Why Next-scale Prediciton Beats Diffusion Models? | Yifan Zhou's Blog

This past April, Peking University (PKU) and ByteDance published a paper on Arxiv titled Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction, introducing a brand-new pa

This past April, Peking University (PKU) and ByteDance published a paper on Arxiv titled Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction, introducing a brand-new paradigm for image generation called Visual Autoregressive Modeling (VAR). This autoregressive generation method represents high-definition images as multi-scale token images and replaces the previously popular next-token prediction with a next-scale prediction approach. On the ImageNet $256×256$ image generation task, VAR outperforms DiT. Our research group was quick to read the paper and found…

saved by

• nicolas

related reading

• [2404.02905] Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictionarxiv.org
• What are Diffusion Models? | Lil'Loglilianweng.github.io
• Scalable Diffusion Models with Transformersopenaccess.thecvf.com
• What are Diffusion Models?lilianweng.github.io
• [2605.05331] ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parametersarxiv.org
• Video Generation Models Explosion 2024yenchenlin.me
• https://arxiv.org/pdf/2006.11239arxiv.org
• State-of-the-Art Image Generative Models – Aran Komatsuzakiarankomatsuzaki.wordpress.com
• [2006.11239] Denoising Diffusion Probabilistic Modelsarxiv.org
• Understanding VQ-VAE (DALL-E Explained Pt. 1)mlberkeley.substack.com
• Fast Training of Diffusion Models with Masked Transformers | PDFarxiv.org
• [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org