Papers › Residual Quantization with Implicit Neural Codebooks

Residual Quantization with Implicit Neural Codebooks

26 Jan 2024arXiv:2401.14732archive 2025-07-28

Iris A. M. Huijben, Matthijs Douze, Matthew Muckley, Ruud J. G. van Sloun, Jakob Verbeek

Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization (RQ) is one such method, which iteratively quantizes the error of the previous step. While the error distribution is dependent on previously-selected codewords, this dependency is not accounted for in conventional RQ as it uses a fixed codebook per quantization step. In this paper, we propose QINCo, a neural RQ variant that constructs specialized codebooks per step that depend on the approximation of the vector from previous steps. Experiments show that QINCo outperforms state-of-the-art methods by a large margin on several datasets and code sizes. For example, QINCo achieves better nearest-neighbor search accuracy using 12-byte codes than the state-of-the-art UNQ using 16 bytes on the BigANN1M and Deep1M datasets.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (3 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

facebookresearch/qinco officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 10 ran (7 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
6ran; the contract check could not run
3ran
3unverified

Licence: 13 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from facebookresearch/qinco. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

facebookresearch/qinco official repository 13 samples, 10 ran (7 instrument-failed) · 3 unverified
IVFBook qinco/model/qinco_base.py ran licence not identified · pointer only · f409546bd6543923 · report fixture: returned tuple · level recorded 2026-09-24
QBlockFFN qinco/model/qinco_base.py ran · metamorphic tier: invariant licence not identified · pointer only · 0154f6c6afc2cfeb · report fixture: signature x_in:Tensor/3/float · returned Tensor · level recorded 2026-09-22
QConcat qinco/model/qinco_base.py ran · metamorphic tier: invariant licence not identified · pointer only · 205ed094438d5ff2 · report fixture: signature zqs:Tensor/2/float, xhat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
approx_compute_batch_distances qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · bc1a701de4211b3d · report fixture: returned Tensor · level recorded 2026-09-22
approx_pairwise_distance qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · e078bbf9885dd047 · report fixture: returned Tensor · level recorded 2026-09-22
compute_batch_distances qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 066d4ad3460ffdf4 · report fixture: returned Tensor · level recorded 2026-09-22
exact_compute_batch_distances qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · ec62f37b60e7ab4c · report fixture: returned Tensor · level recorded 2026-09-22
exact_pairwise_distance qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 71c1f2ab5b80f773 · report fixture: returned Tensor · level recorded 2026-09-22
merge_losses qinco/model/qinco_base.py ran · our draft was wrong licence not identified · pointer only · 3df1936cbc8f5abe · report fixture: signature dest:dict/0/?, src:dict/0/? · returned dict · level recorded 2026-09-24
pairwise_distances in 34 papers
census: 14 implementations from 13 papers, 7 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
qinco/model/qinco_base.py ran; the contract check could not run (RAISES) licence not identified · pointer only · a34f75316e245682 · report fixture: returned Tensor · level recorded 2026-09-22
QINCo qinco/model/qinco_base.py unverified licence not identified · pointer only · 6302cfaf7df6300e · report
QINCoStep qinco/model/qinco_base.py unverified licence not identified · pointer only · 9796e95fac6fb501 · report
QincoSubstep qinco/model/qinco_base.py unverified licence not identified · pointer only · 112cbf1daa7d58cb · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for QINCo (graph method: QINCo). 13 bricks; individually on a fixture: 10 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. QINCo entry · level 0 · unverified · 6302cfaf7df6300e
  2. IVFBook model · level 1 · ran · f409546bd6543923
  3. QINCoStep model · level 0 · unverified · 9796e95fac6fb501
  4. merge_losses helper · level 1 · ran · our draft was wrong · 3df1936cbc8f5abe
  5. approx_pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) · e078bbf9885dd047
  6. QBlockFFN model · level 1 · ran · 0154f6c6afc2cfeb
  7. QConcat model · level 1 · ran · 205ed094438d5ff2
  8. QincoSubstep helper · level 0 · unverified · 112cbf1daa7d58cb
  9. compute_batch_distances helper · level 1 · ran; the contract check could not run (RAISES) · 066d4ad3460ffdf4
  10. pairwise_distances helper · level 1 · ran; the contract check could not run (RAISES) · a34f75316e245682
  11. approx_compute_batch_distances helper · level 1 · ran; the contract check could not run (RAISES) · bc1a701de4211b3d
  12. exact_compute_batch_distances helper · level 1 · ran; the contract check could not run (RAISES) · ec62f37b60e7ab4c
  13. exact_pairwise_distance helper · level 1 · ran; the contract check could not run (RAISES) · 71c1f2ab5b80f773

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2401.14732") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data CompressionQuantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections