# LGQ: Learnable Geometric Quantization for Image Tokenization

Source: [LGQ: Learnable Geometric Quantization for Image Tokenization](<https://www.sota2.com/research/paper/699698e409c33900fcd71d60>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-08T05:00:04.940Z

Authors: Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban

Published: 2026-02-17T23:20:26.000Z

## Abstract

Recent collapse-free quantizers such as FSQ achieve stable training by replacing the learnable codebook with an engineered geometry: a fixed scalar grid whose structure is dictated by the codebook size K. We show this trade-off is unnecessary. We introduce Learnable Geometric Quantization (LGQ), which retains a learnable codebook of codes and performs soft-to-hard assignment via temperature annealing, regularized by two cheap terms: A diversity term scaled by codebook size that penalizes concentrated batch-average usage is the primary driver of collapse resistance, complemented by a peakedness term that sharpens each token's soft-assignment toward one-hot; together they prevent codebook collapse without EMA, reset heuristics, or codebook reparameterization. Under a fixed VQ-GAN backbone, we benchmark LGQ against RotVQ, FSQ, SimVQ, and IBQ on ImageNet 256x256 at K=16,384 and sweep LGQ over K={4096,..,65,536} without any per-K hyperparameter tuning. LGQ attains the best reconstruction FID at K = 16,384 while maintaining 100% codebook utilization, and continues to improve as the codebook grows to K = 65,536 with utilization unchanged. Training MaskGIT on the frozen tokenizers, LGQ further attains the best class-conditional generation among the compared quantizers, leading on reconstruction and generation alike. Code is available at https://github.com/KurbanIntelligenceLab/LGQ.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.16086>)

[PDF](<https://arxiv.org/pdf/2602.16086.pdf>)
