# VLCQ: Post-training quantization for deep neural networks using variable length coding

arXiv: https://arxiv.org/abs/2610.15092 · HTML: https://mlsanity.com/paper/2610.15092/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 10 Oct 2026.

## Builds on (most cited first, 28 of 28)

- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [Object Detection with Deep Learning: A Review](https://mlsanity.com/paper/1807.05511/) (2018)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation](https://mlsanity.com/paper/2004.09602/) (2020)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [Pointwise Convolutional Neural Networks](https://mlsanity.com/paper/1712.05245/) (2017)
- [Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review](https://mlsanity.com/paper/2004.05224/) (2020)
- [APQ: Joint Search for Network Architecture, Pruning and Quantization Policy](https://mlsanity.com/paper/2006.08509/) (2020)
- [Loss Aware Post-training Quantization](https://mlsanity.com/paper/1911.07190/) (2019)
- [Degree-Quant: Quantization-Aware Training for Graph Neural Networks](https://mlsanity.com/paper/2008.05000/) (2020)
- [Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming](https://mlsanity.com/paper/2006.10518/) (2020)
- [Generative Low-bitwidth Data Free Quantization](https://mlsanity.com/paper/2003.03603/) (2020)
- [Data-Free Network Quantization With Adversarial Knowledge Distillation](https://mlsanity.com/paper/2005.04136/) (2020)
- [Post-Training Piecewise Linear Quantization for Deep Neural Networks](https://mlsanity.com/paper/2002.00104/) (2020)
- [Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization](https://mlsanity.com/paper/2110.06554/) (2021)
- [Multimodal Deep Learning for Robust RGB-D Object Recognition](https://mlsanity.com/paper/1507.06821/) (2015)
- [Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision](https://mlsanity.com/paper/2002.09049/) (2020)
- [Large Scale Legal Text Classification Using Transformer Models](https://mlsanity.com/paper/2010.12871/) (2020)
- [Multi-Scale Self-Attention for Text Classification](https://mlsanity.com/paper/1912.00544/) (2019)
- [Deep Learning and Control Algorithms of Direct Perception for Autonomous Driving](https://mlsanity.com/paper/1910.12031/) (2019)
- [Transformer to CNN: Label-scarce distillation for efficient text classification](https://mlsanity.com/paper/1909.03508/) (2019)
- [Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1910.09455/) (2019)
- [Q-YOLO: Efficient Inference for Real-time Object Detection](https://mlsanity.com/paper/2307.04816/) (2023)

## Abstract (arXiv)

Quantization plays a crucial role in efficiently deploying deep learning models on resource-constrained devices. Post-training quantization does not require access to the original dataset or retraining the full model. Current methods that achieve high performance close to baseline results typically require INT8 fixed-point integers. However, achieving higher model compression with lower bit-widths often leads to significant performance degradation. In this paper, we propose VLCQ, a post-training quantization method that relaxes the fixed-point encoding constraint, enabling more flexible exploration of quantization techniques through variable-length encoding. This approach achieves competitive or improved performance while reducing bit-widths, without requiring access to training data or model fine-tuning. Extensive experiments on image classification, segmentation, and object detection demonstrate that VLCQ improves model compression and accuracy compared with state-of-the-art post-training quantization approaches. For per-channel quantization, VLCQ surpasses FP32 accuracy and Piece-Wise Linear Quantization (PWLQ) on most evaluated models, achieving up to 6x compression compared with FP32 and up to 1.7x compared with PWLQ. When prioritizing compression with limited accuracy loss, VLCQ achieves up to 12.25x compression compared with FP32 with less than 4% performance degradation. For per-tensor quantization, VLCQ is competitive with Data-Free Quantization (DFQ), while providing greater flexibility to achieve lower bit rates across different tasks and models.