Papers › General-purpose, long-context autoregressive modeling with Perceiver AR

General-purpose, long-context autoregressive modeling with Perceiver AR

15 Feb 2022arXiv:2202.07765archive 2025-07-28

Curtis Hawthorne, Andrew Jaegle, Cătălina Cangea, Sebastian Borgeaud, Charlie Nash, Mateusz Malinowski, Sander Dieleman, Oriol Vinyals, Matthew Botvinick, Ian Simon, Hannah Sheahan, Neil Zeghidour, Jean-Baptiste Alayrac, João Carreira, Jesse Engel

Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly used autoregressive models, Transformers, are prohibitively expensive to scale to the number of inputs and layers needed to capture this long-range structure. We develop Perceiver AR, an autoregressive, modality-agnostic architecture which uses cross-attention to map long-range inputs to a small number of latents while also maintaining end-to-end causal masking. Perceiver AR can directly attend to over a hundred thousand tokens, enabling practical long-context density estimation without the need for hand-crafted sparsity patterns or memory mechanisms. When trained on images or music, Perceiver AR generates outputs with clear long-term coherence and structure. Our architecture also obtains state-of-the-art likelihood on long-sequence benchmarks, including 64 x 64 ImageNet images and PG-19 books.

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 12 code samples harvested from 3 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 11 samples from 2 repositories, 8 ran (5 with no instrument failure; 3 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. 2 of the 9 samples that ran have no recorded date.

google-research/perceiver-ar officialmentioned in papermentioned on GitHubjaxSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
krasserm/perceiver-io mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
lucidrains/perceiver-ar-pytorch mentioned on GitHubpytorchSyntology: 9 samples, 6 ran (3 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

12 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 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.

4ran · our draft was wrong
5ran
3unverified

Licence: 1 of the 12 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 3 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”. “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.

google-research/perceiver-ar official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_sweep in 7 papers perceiver_ar/experiment.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 · our draft was wrong licence of this copy not recorded · 3ce096de610c4729 · report fixture: signature sweep_name:str/0/str, train_device_count:int/0/int, eval_device_count:int/0/int · returned list · level recorded, date not recorded
krasserm/perceiver-io community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
is_checkpoint perceiver/model/core/lightning.py ran Apache-2.0 (permissive) · 9ac70921db9fdb73 · report fixture: signature path:str/0/str · returned bool · level recorded 2026-09-24
positions perceiver/model/core/position.py ran Apache-2.0 (permissive) · 6534b6aca89ab357 · report fixture: signature b:int/0/int, n:int/0/int, shift:Tensor/2/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
lucidrains/perceiver-ar-pytorch community (archive-listed) 9 samples, 6 ran (3 instrument-failed) · 3 unverified
CausalAttention perceiver_ar_pytorch/perceiver_ar_pytorch.py ran · metamorphic tier: invariant MIT (permissive) · a265de65b3c70e54 · report fixture: signature x:Tensor/3/float, rotary_pos_emb:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CausalPrefixAttention perceiver_ar_pytorch/perceiver_ar_pytorch.py ran MIT (permissive) · 90ebd55fce80e55d · report fixture: signature x:Tensor/3/float, context:Tensor/3/float, context_mask:Tensor/2/bool, rotary_pos_emb:Tensor/3/float · returned Tensor · level recorded 2026-09-24
FeedForward in 198 papers perceiver_ar_pytorch/perceiver_ar_pytorch.py ran · our draft was wrong MIT (permissive) · 7e6f6a18c63a8be3 · report fixture: signature dim:int/0/int, mult:int/0/int, dropout:float/0/float · returned Sequential · level recorded 2026-09-22
RotaryEmbedding in 27 papers perceiver_ar_pytorch/perceiver_ar_pytorch.py ran · metamorphic tier: well formed MIT (permissive) · f8c62fb6aaac766d · report fixture: signature max_seq_len:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
apply_rotary_pos_emb in 393 papers
census: 14 implementations from 15 papers, 8 distinct outputs across 7 buckets, one shared input per bucket this sample: bucket 2 of 7, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
perceiver_ar_pytorch/perceiver_ar_pytorch.py ran · our draft was wrong MIT (permissive) · 746466b4822c61fb · report fixture: signature pos:Tensor/3/float, t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
perceiver_ar_pytorch/perceiver_ar_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) · 1964789ef2be9b81 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
FeedForward in 198 papers perceiver_ar_pytorch/perceiver_ar_pytorch.py unverified MIT (permissive) · 7599a08b755aee53 · report
PerceiverAR perceiver_ar_pytorch/perceiver_ar_pytorch.py unverified MIT (permissive) · d0f7f44834342f9f · 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 Perceiver AR (graph method: Perceiver AR). 8 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. PerceiverAR entry · level 0 · unverified · d0f7f44834342f9f
  2. CausalAttention model · level 1 · ran · a265de65b3c70e54
  3. CausalPrefixAttention model · level 1 · ran · 90ebd55fce80e55d
  4. FeedForward model · level 1 · ran · our draft was wrong · 7e6f6a18c63a8be3
  5. RotaryEmbedding model · level 1 · ran · f8c62fb6aaac766d
  6. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  7. apply_rotary_pos_emb model · level 1 · ran · our draft was wrong · 746466b4822c61fb
  8. rotate_half helper · level 1 · ran · our draft was wrong · fdd93453f92f9167

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="2202.07765") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Density EstimationLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling WikiText-103 Perceiver AR 358M Test perplexity 18.4 #36 of 89 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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