Megadose AI progress, ranked and analyzed.

StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training

· HF Daily Papers ·
StableVQ targets the training instability that can make vector-quantized visual tokenizers fail under stress.

The paper argues the problem comes from encoder-decoder and codebook objectives being too entangled. Its three changes are Dynamic STE, Region VQ Loss, and a Decoupled Schedule for separate optimization dynamics. The method is built on shared-projection codebooks and adds no learnable parameters. On ImageNet, the authors report better stability, codebook utilization, and reconstruction quality across codebook sizes and initialization settings. HF Daily Papers' note

score 5

Categories: Research