Skip to main content
Search

# Grouped Product Quantization

1 related articles

Subscribe to updates
  1. arXiv

    Discrete codes can carry vision too: dNaViT uses one codebook for understanding, reconstruction and generation

    dNaViT encodes images into discrete codes of the same kind language models predict, and one shared vocabulary serves visual understanding, image reconstruction, generation and editing. It builds on a frozen pretrained vision encoder, adds reconstruction-relevant detail through residual modulation, and uses grouped product quantization to widen discrete capacity without lengthening the spatial sequence. On ImageNet-1K, the 64-group dNaViT-G64 reaches 32.90 dB PSNR and 0.91 SSIM at 1024 spatial positions, and dNaViT-8B paired with Qwen3-8B scores 885 on OCRBench.

You’re all caught up