Papers › HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

27 Jun 2023NeurIPS 2023 11arXiv:2306.15794archive 2025-07-28

Eric Nguyen, Michael Poli, Marjan Faizi, Armin Thomas, Callum Birch-Sykes, Michael Wornow, Aman Patel, Clayton Rabideau, Stefano Massaroli, Yoshua Bengio, Stefano Ermon, Stephen A. Baccus, Chris Ré

Genomic (DNA) sequences encode an enormous amount of information for gene regulation and protein synthesis. Similar to natural language models, researchers have proposed foundation models in genomics to learn generalizable features from unlabeled genome data that can then be fine-tuned for downstream tasks such as identifying regulatory elements. Due to the quadratic scaling of attention, previous Transformer-based genomic models have used 512 to 4k tokens as context (<0.001% of the human genome), significantly limiting the modeling of long-range interactions in DNA. In addition, these methods rely on tokenizers or fixed k-mers to aggregate meaningful DNA units, losing single nucleotide resolution where subtle genetic variations can completely alter protein function via single nucleotide polymorphisms (SNPs). Recently, Hyena, a large language model based on implicit convolutions was shown to match attention in quality while allowing longer context lengths and lower time complexity. Leveraging Hyena's new long-range capabilities, we present HyenaDNA, a genomic foundation model pretrained on the human reference genome with context lengths of up to 1 million tokens at the single nucleotide-level - an up to 500x increase over previous dense attention-based models. HyenaDNA scales sub-quadratically in sequence length (training up to 160x faster than Transformer), uses single nucleotide tokens, and has full global context at each layer. We explore what longer context enables - including the first use of in-context learning in genomics. On fine-tuned benchmarks from the Nucleotide Transformer, HyenaDNA reaches state-of-the-art (SotA) on 12 of 18 datasets using a model with orders of magnitude less parameters and pretraining data. On the GenomicBenchmarks, HyenaDNA surpasses SotA on 7 of 8 datasets on average by +10 accuracy points. Code at https://github.com/HazyResearch/hyena-dna.

PaperPDFConference PDFCodeCode 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 28 code samples harvested from 2 repositories linked to this paper: 17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 5 ran (3 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 20 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

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. 1 of the 17 samples that ran has no recorded date.

HazyResearch/hyena-dna officialmentioned in papermentioned on GitHubpytorchSyntology: 8 samples, 5 ran (2 instrument-failed) · 3 unverified report
frederikkemarin/bend mentioned on GitHubpytorchBSD-3-ClauseSyntology: 20 samples, 12 ran (2 instrument-failed) · 8 unverified report
jimmylihui/OpenGenome mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling (arXiv:2403.03234; that paper's own run record: 9 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
jimmylihui/genbench mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modeling (arXiv:2403.03234; that paper's own run record: 9 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

28 samples harvested: 17 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 11 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.

3ran · our draft was wrong
1ran; the contract check could not run
13ran
11unverified

Licence: 1 of the 28 samples is 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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”. For 8 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

HazyResearch/hyena-dna official repository 8 samples, 5 ran (2 instrument-failed) · 3 unverified
Activation in 28 papers src/models/sequence/hyena.py ran · our draft was wrong Apache-2.0 (permissive) · 3cd2f572b4362749 · report fixture: signature activation:str/0/str, size:NoneType/0/?, dim:int/0/int · returned ReLU · level recorded 2026-09-22
Laplace in 5 papers src/models/sequence/hyena.py ran fingerprinted Apache-2.0 (permissive) · 916ff67d7cc5dec1 · report fixture: returned Laplace · level recorded 2026-09-22
SquaredReLU src/models/sequence/hyena.py ran fingerprinted Apache-2.0 (permissive) · 2c0fd690964e38f6 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
TransposedLN src/models/sequence/hyena.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · f930c490ea93d623 · report fixture: returned TransposedLN · level recorded 2026-09-22
laplace in 12 papers src/models/sequence/hyena.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 452d521c52ebdf0f · report fixture: signature x:Tensor/2/float, mu:float/0/float, sigma:float/0/float · returned Tensor · level recorded 2026-09-22
HyenaOperator src/models/sequence/hyena.py unverified Apache-2.0 (permissive) · bdfcfc1b78dd3774 · report
auto_assign_attrs src/models/sequence/hyena.py unverified Apache-2.0 (permissive) · b37e90eb829295dc · report
instantiate src/models/sequence/hyena.py unverified Apache-2.0 (permissive) · ef3e1ed020307a6f · report
frederikkemarin/bend community (archive-listed) 20 samples, 12 ran (2 instrument-failed) · 8 unverified
ExponentialModulation bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · 71c56d498ff19d96 · report fixture: returned ExponentialModulation · level recorded 2026-09-22
GPT2Embeddings bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · fb99304499c57d08 · report fixture: returned GPT2Embeddings · level recorded 2026-09-22
HyenaFilter bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · b65ebc2556b1f0bd · report fixture: returned HyenaFilter · level recorded 2026-09-22
LinearResidual bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · e9b64f401a36c5e0 · report fixture: returned LinearResidual · level recorded 2026-09-22
MHA in 5 papers bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · 2108a9e482ae37a6 · report fixture: returned MHA · level recorded 2026-09-22
Mlp in 102 papers bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · d86ea40df8708d4d · report fixture: returned Mlp · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · 0e977f11203102fd · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
SelfAttention in 66 papers bend/models/hyena_dna.py ran fingerprinted BSD-3-Clause (permissive) · f745e0dbcc9bb059 · report fixture: signature qkv:Tensor/5/float, causal:NoneType/0/?, key_padding_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
SequenceDecoder bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · d30504da4d509b40 · report fixture: returned SequenceDecoder · level recorded 2026-09-22
Sin in 6 papers bend/models/hyena_dna.py ran BSD-3-Clause (permissive) · 3f162814e9da788b · report fixture: returned Sin · level recorded 2026-09-22
create_mlp_cls bend/models/hyena_dna.py ran · our draft was wrong BSD-3-Clause (permissive) · f365c364e5fb2475 · report fixture: signature d_model:int/0/int, d_inner:int/0/int, device:NoneType/0/?, dtype:NoneType/0/? · returned partial · level recorded 2026-09-22
mul_sum in 9 papers bend/models/hyena_dna.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 5dd28d20c60f0c19 · report fixture: returned Tensor · level recorded, date not recorded
HyenaDNAModel bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 1a0693ded9212e71 · report
HyenaOperator bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 7b17a3ba43c38567 · report
LMBackbone bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 989ba1bad54bbbc8 · report
_init_weights in 9 papers bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 8ae5fabb54f1ee70 · report
create_block in 13 papers bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 78db10ce14ffa95c · report
create_mixer_cls bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · fe93a5054c8dd38f · report
fftconv bend/models/hyena_dna.py unverified BSD-3-Clause (permissive) · 41b32f57fc8ec1e5 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for HyenaDNA (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for HyenaDNA (graph method: HyenaDNA). 9 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. HyenaOperator entry · level 0 · unverified · bdfcfc1b78dd3774
  2. Activation helper · level 1 · ran · our draft was wrong · 3cd2f572b4362749
  3. auto_assign_attrs helper · level 0 · unverified · b37e90eb829295dc
  4. instantiate helper · level 0 · unverified · ef3e1ed020307a6f
  5. mul_sum helper · level 1 · ran; the contract check could not run (RAISES) · 5dd28d20c60f0c19
  6. Laplace helper · level 1 · ran · 916ff67d7cc5dec1
  7. SquaredReLU helper · level 1 · ran · 2c0fd690964e38f6
  8. TransposedLN helper · level 1 · ran · f930c490ea93d623
  9. laplace helper · level 1 · ran · our draft was wrong · 452d521c52ebdf0f

harvested Assembly for HyenaDNA (graph method: HyenaDNA). 20 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. HyenaDNAModel entry · level 0 · unverified · 1a0693ded9212e71
  2. LMBackbone model · level 0 · unverified · 989ba1bad54bbbc8
  3. SequenceDecoder model · level 1 · ran · d30504da4d509b40
  4. _init_weights helper · level 0 · unverified · 8ae5fabb54f1ee70
  5. GPT2Embeddings helper · level 1 · ran · fb99304499c57d08
  6. create_block helper · level 0 · unverified · 78db10ce14ffa95c
  7. Block model · level 0 · unverified · 15e87d04566e903e
  8. create_mixer_cls helper · level 0 · unverified · fe93a5054c8dd38f
  9. create_mlp_cls helper · level 1 · ran · our draft was wrong · f365c364e5fb2475
  10. MHA helper · level 1 · ran · 2108a9e482ae37a6
  11. Mlp helper · level 1 · ran · d86ea40df8708d4d
  12. HyenaOperator model · level 0 · unverified · 7b17a3ba43c38567
  13. LinearResidual helper · level 1 · ran · e9b64f401a36c5e0
  14. SelfAttention helper · level 1 · ran · f745e0dbcc9bb059
  15. HyenaFilter model · level 1 · ran · b65ebc2556b1f0bd
  16. ExponentialModulation model · level 1 · ran · 71c56d498ff19d96
  17. OptimModule helper · level 0 · unverified · 6f2ce45de2079602
  18. PositionalEmbedding model · level 1 · ran · 0e977f11203102fd
  19. Sin helper · level 1 · ran · 3f162814e9da788b
  20. fftconv helper · level 0 · unverified · 41b32f57fc8ec1e5

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="2306.15794") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

4kIn-Context LearningLanguage ModellingLarge Language Model

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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