🚀 Introducing scale and spatial Markovian assumptions into VAR — achieving faster generation with reduced memory consumption.

[NuanBaobao]

Thanks to the great work on VAR! 🙌
Building upon it, we introduce MVAR, which incorporates scale and spatial Markovian assumptions into visual autoregressive modeling.
MVAR achieves a 1.7× speedup and 3× reduction in GPU memory usage, enabling efficient training on eight RTX 4090 GPUs.

📄 Paper: https://arxiv.org/abs/2505.1274
🔗 GitHub: https://github.com/LabShuHangGU/MVAR

[NuanBaobao]

@enjoyyi00 , Hello, thank you very much for VAR’s outstanding contributions to the open-source community.

Our work MVAR has been accepted to ICLR 2026. If possible, we would be honored if MVAR could be included as a reference or link in your README. We sincerely appreciate VAR’s impactful work and its support of open research.

Project page:
https://nuanbaobao.github.io/MVAR

Thank you again for your time and contributions.