SOURCE-LINKED INTELLIGENCE

LoopVAE: Recurrent Depth Across Scales for Visual Tokenization

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Hierarchical visual tokenizers typically allocate different processing blocks to different spatial scales. We ask how much of this computation can use the same parameters. LoopVAE reuses a scale- and loop-conditioned core within and across scales, while keeping resolution-changing transitions independent. A four-block core executes 28 block applications per encoder or decoder. On ImageNet-256, the 29M-parameter convolutional model reaches 0.28 rFID and 32.54 dB PSNR under an approximately 30-epoch two-stage training budget, using approximately 65% fewer parameters than the 84M reference VAEs.

Read original source ↗ Open in workspace

recordType

paper

region

Global