mlsanityData to 7 Oct 2026

LL-VQ-VAE: Learnable Lattice Vector-Quantization For Efficient Representations

arXiv 2310.09382 ↗First posted 13 Oct 2023cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper we introduce learnable lattice vector quantization and demonstrate its effectiveness for learning discrete representations. Our method, termed LL-VQ-VAE, replaces the vector quantization layer in VQ-VAE with lattice-based discretization. The learnable lattice imposes a structure over all discrete embeddings, acting as a deterrent against codebook collapse, leading to high codebook utilization. Compared to VQ-VAE, our method obtains lower reconstruction errors under the same training conditions, trains in a fraction of the time, and with a constant number of parameters (equal to the embedding dimension D), making it a very scalable approach. We demonstrate these results on the FFHQ-1024 dataset and include FashionMNIST and Celeb-A.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 35 references that are in the map. First posted on arXiv 13 Oct 2023.

Builds on

22 of 35 references.

References · 22

  1. 2017Neural Discrete Representation Learningcited by 4,650
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  4. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  7. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  8. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  9. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  10. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  11. 2016Pixel Recurrent Neural Networkscited by 814
  12. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
10 more
  1. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  2. 2014Neural Variational Inference and Learning in Belief Networkscited by 116
  3. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  4. 2016Variational inference for Monte Carlo objectivescited by 83
  5. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  6. 2020Hierarchical Quantized Autoencoderscited by 55
  7. 2020Robust Training of Vector Quantized Bottleneck Modelscited by 53
  8. 2023LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compressioncited by 19
  9. 2018Universal Deep Neural Network Compressioncited by 17
  10. 2020Lattice Representation Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantizationcited by 12
  2. 2024Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compressioncited by 8
  3. 2025Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compressioncited by 4
  4. 2025Receptive Field Expanded Look-Up Tables for Vision Inference: Advancing from Low-level to High-level Taskscited by 1