José Hernández-Lobato, Jie Tang, Yan Wang, Wendi Zheng, Tongda Xu, Ya-Qin Zhang, Jiajun He
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vector-quantized variational autoencoders (VQ-VAEs) are discrete autoencoders that compress images into discrete tokens. However, they are difficult to train due to discretization. In this paper, we propose a simple yet effective technique dubbed Gaussian Quant (GQ), which first trains a Gaussian VAE under certain constraints and then converts it into a VQ-VAE without additional training. For conversion, GQ generates random Gaussian noise as a codebook and finds the closest noise vector to the posterior mean. Theoretically, we prove that when the logarithm of the codebook size exceeds the bits-back coding rate of the Gaussian VAE, a small quantization error is guaranteed. Practically, we propose a heuristic to train Gaussian VAEs for effective conversion, named the target divergence constraint (TDC). Empirically, we show that GQ outperforms previous VQ-VAEs, such as VQGAN, FSQ, LFQ, and BSQ, on both UNet and ViT architectures. Furthermore, TDC also improves previous Gaussian VAE discretization methods, such as TokenBridge. The source code is provided in https://github.com/tongdaxu/VQ-V AE-from-Gaussian-VAE.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2512.06609")
get_code_for_paper("2512.06609")
have("2512.06609")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2512.06609.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2512.06609)
Connect an agent — have() is free.