# Qinco2: Vector Compression and Search with Improved Implicit Neural Codebooks

arXiv: https://arxiv.org/abs/2501.03078 · HTML: https://mlsanity.com/paper/2501.03078/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Builds on (most cited first, 14 of 14)

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Towards image compression with perfect realism at ultra-low bitrates](https://mlsanity.com/paper/2310.10325/) (2023)
- [Online Clustered Codebook](https://mlsanity.com/paper/2307.15139/) (2023)
- [Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2205.03763/) (2022)
- [Image Compression with Product Quantized Masked Image Modeling](https://mlsanity.com/paper/2212.07372/) (2022)
- [Residual Quantization with Implicit Neural Codebooks](https://mlsanity.com/paper/2401.14732/) (2024)
- [Unsupervised Neural Quantization for Compressed-Domain Similarity Search](https://mlsanity.com/paper/1908.03883/) (2019)
- [Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search](https://mlsanity.com/paper/1509.05195/) (2015)
- [Rate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models](https://mlsanity.com/paper/2405.14222/) (2024)

## Built on by (most cited first, 8 of 8)

- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [RQ-MoE: Residual Quantization via Mixture of Experts for Efficient Input-Dependent Vector Compression](https://mlsanity.com/paper/2605.14359/) (2026)
- [Machine learning and high dimensional vector search](https://mlsanity.com/paper/2502.16931/) (2025)
- [Multi-Bitwidth Quantization for LLMs Using Additive Codebooks](https://mlsanity.com/paper/2606.12876/) (2026)
- [Embedding Compression via Spherical Coordinates](https://mlsanity.com/paper/2602.00079/) (2026)
- [S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization](https://mlsanity.com/paper/2602.15082/) (2026)
- [RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2608.30384/) (2026)
- [MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search](https://mlsanity.com/paper/2610.03651/) (2026)

## Abstract (arXiv)

Vector quantization is a fundamental technique for compression and large-scale nearest neighbor search. For high-accuracy operating points, multi-codebook quantization associates data vectors with one element from each of multiple codebooks. An example is residual quantization (RQ), which iteratively quantizes the residual error of previous steps. Dependencies between the different parts of the code are, however, ignored in RQ, which leads to suboptimal rate-distortion performance. QINCo recently addressed this inefficiency by using a neural network to determine the quantization codebook in RQ based on the vector reconstruction from previous steps. In this paper we introduce QINCo2 which extends and improves QINCo with (i) improved vector encoding using codeword pre-selection and beam-search, (ii) a fast approximate decoder leveraging codeword pairs to establish accurate short-lists for search, and (iii) an optimized training procedure and network architecture. We conduct experiments on four datasets to evaluate QINCo2 for vector compression and billion-scale nearest neighbor search. We obtain outstanding results in both settings, improving the state-of-the-art reconstruction MSE by 34% for 16-byte vector compression on BigANN, and search accuracy by 24% with 8-byte encodings on Deep1M.