Papers › Perceiver: General Perception with Iterative Attention
Perceiver: General Perception with Iterative Attention
Andrew Jaegle, Felix Gimeno, Andrew Brock, Andrew Zisserman, Oriol Vinyals, Joao Carreira
Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.
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):
get_harvested_code_for_paper(arxiv_id="2103.03206")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2103.03206", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2103.03206")
Code
Syntology 55 code samples: 54 from 11 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 55: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 1 sample from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 49 samples from 9 repositories, 36 ran (28 with no instrument failure; 8 where Syntology's instrument failed); community: 4 samples from 1 repository, 4 ran (1 with no instrument failure; 3 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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:
- krasserm/perceiver-io, community (archive-listed): harvested for another paper, listed under the repository
- yangyucheng000/University, community (archive-listed): harvested for another paper, listed under the repository
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. 6 of the 41 samples that ran have no recorded date.
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
55 samples harvested: 41 ran (of which 20 constructed an object rather than computing a result; 30 with no instrument failure: 0 honoured, 2 violated, 28 with no contract checked; 11 where Syntology's instrument failed) · 14 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.
Licence: 11 of the 55 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 11 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 is listed last, in a group without a repository. “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 5 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.
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket perceiver/perceiver.py ran MIT (permissive) ·
2b6160b81f7900b0 · report
fixture: returned Attention · level recorded 2026-09-22 ef7ed09adef36f64 · report
fixture: returned FeedForward · level recorded 2026-09-22 census: 12 implementations from 12 papers, 1 distinct output on one shared input perceiver/perceiver.py ran MIT (permissive) ·
7bcff3ae8d60e20e · report
fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24 49b3ac32977e5194 · report
fixture: returned Perceiver · level recorded 2026-09-22 05438d49f4565e5e · report
fixture: returned PreNorm · level recorded 2026-09-22 81535522703627e2 · report
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket perceiver_pytorch/perceiver_pytorch.py ran · metamorphic tier: invariant MIT (permissive) ·
dab3a202eec902f5 · report
fixture: signature x:Tensor/3/float, context:Tensor/3/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-22 d5ad02791f6342b3 · report
b88fa1918b8c2d8e · report
9573db9d1cb8488b · report
census: 5 implementations from 103 papers, 1 distinct output on one shared input perceiver_pytorch/perceiver_pytorch.py unverified MIT (permissive) ·
3f47658c584c3676 · report
d7a83e087ca450f4 · report
fixture: returned FeedForward · level recorded 2026-09-22 census: 12 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 utils/perceiver.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only ·
7852fe36c3e3b1f9 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket utils/perceiver.py unverified no licence file found · pointer only ·
c78772b126a7d1bf · report
17bf6227f2dcfc36 · report
5a52aee4bb4c2cf2 · report
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket perceiver_pytorch/perceiver_pytorch.py ran MIT (permissive) ·
b908a940626ba009 · report
fixture: returned Attention · level recorded 2026-09-22 ac1c3509b3aee38c · report
fixture: returned Perceiver · level recorded 2026-09-22 6f367de5d5a82e44 · report
fixture: returned PreNorm · level recorded 2026-09-22 f449e2a5647debf4 · report
fixture: signature f:callable/0/? · returned function · level recorded 2026-09-22 2db56d1fa509f735 · report
fixture: signature x:Tensor/2/float, max_freq:float/0/float, num_bands:int/0/int, base:int/0/int · returned Tensor · level recorded 2026-09-22 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket model/attention.py ran no licence file found · pointer only ·
407c9004f3d03831 · report
fixture: signature x:Tensor/3/float, context:Tensor/3/float, mask:Tensor/2/bool · returned Tensor · level recorded 2026-09-24 122a2bb1f3342e5c · report
fixture: returned CrossAttention · level recorded 2026-09-22 b04a1cb2350af23e · report
fixture: returned FeedForward · level recorded 2026-09-22 9a15eee5a72a53ec · report
fixture: returned PreNorm · level recorded 2026-09-22 a72f0467d5ab04ca · report
fixture: signature x:Tensor/2/float, max_freq:float/0/float, num_bands:int/0/int · returned Tensor · level recorded 2026-09-22 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket perceiver_pytorch/perceiver_pytorch.py ran · metamorphic tier: deterministic MIT (permissive) ·
1f325569b6d0c2df · report
fixture: returned Attention · level recorded 2026-09-22 9cc277014f5865d5 · report
fixture: returned FeedForward · level recorded 2026-09-22 census: 12 implementations from 12 papers, 1 distinct output on one shared input perceiver_pytorch/perceiver_pytorch.py ran fingerprinted MIT (permissive) ·
7dda3cde0f4a0d98 · report
fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24 5a2b853142bcff22 · report
fixture: returned Perceiver · level recorded 2026-09-22 3c2027fdf007f1d3 · report
fixture: returned PreNorm · level recorded 2026-09-22 7764f517d3e13e73 · report
fixture: signature x:Tensor/2/float, max_freq:float/0/float, num_bands:int/0/int · returned Tensor · level recorded 2026-09-22 census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 perceiver_pytorch/perceiver_pytorch.py ran; the contract check could not run (DEP_MISSING) · metamorphic tier: invariant fingerprinted MIT (permissive) ·
f1ef7aeee4ed2d74 · report
fixture: signature t:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded, date not recorded census: 7 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 perceiver_pytorch/perceiver_pytorch.py ran · our draft was wrong fingerprinted MIT (permissive) ·
52649c5bdcbe1d0a · report
fixture: signature t:Tensor/2/float, dim:int/0/int, eps:float/0/float · returned Tensor · level recorded 2026-09-22 e56401f8aa027f99 · report
2192232b9e8a1557 · report
census: 5 implementations from 103 papers, 1 distinct output on one shared input perceiver_pytorch/perceiver_pytorch.py unverified MIT (permissive) ·
eb158ba777c1217c · report
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket perceiver_jax/perceiver_jax.py ran MIT (permissive) ·
9a7903b6b454a21a · report
fixture: returned Attention · level recorded 2026-09-22 829093ff624cc3ea · report
fixture: returned FeedForward · level recorded 2026-09-22 8d50746971d74b4a · report
fixture: signature x:ArrayImpl/2/float, num_encodings:int/0/int · returned ArrayImpl · level recorded 2026-09-22 765c0c81701efcfc · report
fixture: returned Perceiver · level recorded 2026-09-22 28861a4c4ddbb06a · report
fixture: signature x:Tensor/3/float, z_input:Tensor/3/float · returned Tensor · level recorded 2026-09-24 28e6bb621fe7b050 · report
fixture: returned PerceiverBlock · level recorded 2026-09-22 69c8bf0af95ad719 · report
fixture: returned PerceiverBlockRepeater · level recorded 2026-09-22 088d7be4e21dbe4f · report
fixture: signature shape:tuple/1/int, bands:int/0/int · returned Tensor · level recorded 2026-09-22 ce5db0a13e19e003 · report
fixture: signature x_q:Tensor/3/float, x_kv:Tensor/3/float, pad_mask:NoneType/0/?, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22 census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket towhee/models/perceiver/cross_attention.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) ·
055997cbf4c57dd0 · report
fixture: signature x_q:Tensor/3/float, x_kv:Tensor/3/float, pad_mask:NoneType/0/?, attn_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22 d1297a0c047d6cb7 · report
fixture: signature a:ArrayImpl/3/float, val:float/0/float · returned ArrayImpl · level recorded, date not recorded 3fa4cf728bbb0dff · report
fixture: signature sequence:ArrayImpl/1/float · returned ArrayImpl · level recorded, date 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 1357068f980451b5 · report
fixture: signature sequence:ArrayImpl/1/int · returned ArrayImpl · level recorded, date not recorded 1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
7c49b92babb27a7d · report
fixture: signature val:NoneType/0/?, d:int/0/int · returned int · level recorded, date not recorded 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.
10 assemblies on this paper: 10 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
10 sibling assemblies for Perceiver (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.
harvested Assembly for Perceiver (graph method: Perceiver). 5 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 1 · ran ·
765c0c81701efcfc - PerceiverBlock model · level 1 · ran ·
28e6bb621fe7b050 - PerceiverBlockRepeater model · level 1 · ran ·
69c8bf0af95ad719 - fourier_features data_transform · level 1 · ran · our draft was wrong ·
088d7be4e21dbe4f - PerceiverAttentionBlock model · level 1 · ran ·
28861a4c4ddbb06a
harvested Assembly for Perceiver (graph method: Perceiver). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 1 · ran ·
49b3ac32977e5194 - Attention model · level 1 · ran ·
2b6160b81f7900b0 - FeedForward model · level 1 · ran ·
ef7ed09adef36f64 - PreNorm model · level 1 · ran ·
05438d49f4565e5e - fourier_encode helper · level 0 · unverified ·
81535522703627e2 - GEGLU helper · level 1 · ran ·
7bcff3ae8d60e20e
harvested Assembly for Perceiver (graph method: Perceiver). 5 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 0 · unverified ·
17bf6227f2dcfc36 - Attention model · level 0 · unverified ·
c78772b126a7d1bf - FeedForward helper · level 1 · ran ·
d7a83e087ca450f4 - PreNorm helper · level 0 · unverified ·
5a52aee4bb4c2cf2 - GEGLU helper · level 1 · ran ·
7852fe36c3e3b1f9
harvested Assembly for Perceiver (graph method: Perceiver). 10 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 1 · ran ·
5a2b853142bcff22 - Attention model · level 1 · ran ·
1f325569b6d0c2df - FeedForward helper · level 1 · ran ·
9cc277014f5865d5 - PreNorm helper · level 1 · ran ·
3c2027fdf007f1d3 - cache_fn helper · level 0 · unverified ·
e56401f8aa027f99 - fourier_encode data_transform · level 1 · ran · our draft was wrong ·
7764f517d3e13e73 - default helper · level 1 · ran · violated contract ·
60fff7c3c400d7ff - exists helper · level 1 · ran · violated contract ·
aa5486a3650902d8 - l1norm helper · level 1 · ran · our draft was wrong ·
52649c5bdcbe1d0a - GEGLU helper · level 1 · ran ·
7dda3cde0f4a0d98
harvested Assembly for Perceiver (graph method: Perceiver). 8 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- CrossAttention entry · level 1 · ran ·
122a2bb1f3342e5c - Attention helper · level 1 · ran ·
407c9004f3d03831 - FeedForward model · level 1 · ran ·
b04a1cb2350af23e - PreNorm helper · level 1 · ran ·
9a15eee5a72a53ec - fourier_encode helper · level 1 · ran · our draft was wrong ·
a72f0467d5ab04ca - default helper · level 1 · ran · violated contract ·
60fff7c3c400d7ff - exists helper · level 1 · ran · violated contract ·
aa5486a3650902d8 - GEGLU helper · level 1 · ran ·
384419959d31762c
harvested Assembly for Perceiver (graph method: Perceiver). 6 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 0 · unverified ·
814bc971d852a52e - Attention model · level 1 · ran ·
9a7903b6b454a21a - FeedForward model · level 1 · ran ·
829093ff624cc3ea - ReZero model · level 0 · unverified ·
41eca8c534139e86 - fourier_encode data_transform · level 1 · ran; the contract check could not run (RAISES) ·
8d50746971d74b4a - default helper · level 2 · ran · violated contract ·
7c49b92babb27a7d
harvested Assembly for Perceiver (graph method: Perceiver). 9 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 1 · ran ·
ac1c3509b3aee38c - Attention model · level 1 · ran ·
b908a940626ba009 - FeedForward model · level 1 · ran ·
0183b5f0d306482f - PreNorm helper · level 1 · ran ·
6f367de5d5a82e44 - cache_fn helper · level 1 · ran · our draft was wrong ·
f449e2a5647debf4 - fourier_encode data_transform · level 1 · ran · our draft was wrong ·
2db56d1fa509f735 - default helper · level 1 · ran · violated contract ·
60fff7c3c400d7ff - exists helper · level 1 · ran · violated contract ·
aa5486a3650902d8 - GEGLU helper · level 1 · ran ·
384419959d31762c
harvested Assembly for Perceiver (graph method: Perceiver). 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- CrossAttention entry · level 1 · ran ·
ce5db0a13e19e003 - MultiHeadAttention helper · level 1 · ran ·
055997cbf4c57dd0
harvested Assembly for Perceiver (graph method: Perceiver). 9 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 0 · unverified ·
d5ad02791f6342b3 - Attention model · level 1 · ran ·
dab3a202eec902f5 - FeedForward helper · level 1 · ran ·
0183b5f0d306482f - PreNorm helper · level 1 · ran ·
6f367de5d5a82e44 - cache_fn helper · level 1 · ran · our draft was wrong ·
8458f9ba0361ff43 - fourier_encode data_transform · level 1 · ran · our draft was wrong ·
2db56d1fa509f735 - default helper · level 1 · ran · violated contract ·
60fff7c3c400d7ff - exists helper · level 1 · ran · violated contract ·
aa5486a3650902d8 - GEGLU helper · level 1 · ran ·
384419959d31762c
harvested Assembly for Perceiver (graph method: Perceiver). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 10 siblings
- Perceiver entry · level 0 · unverified ·
5f128411733f3d4d
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="2103.03206") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Point Cloud Classification | ModelNet40 | Perceiver | Mean Accuracy | 14.3 | #111 of 111 | Archive leaderboard | report |
| Audio Classification | AudioSet | Perceiver | Test mAP | 0.449 | #39 of 51 | Archive leaderboard | report |
| Image Classification | ImageNet | Perceiver (FF) | GFLOPs | 707.2 | #858 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Perceiver (FF) | Number of params | 44.9M | #858 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Perceiver (FF) | Top 1 Accuracy | 78% | #858 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Perceiver | Top 1 Accuracy | 76.4% | #913 of 1060 | 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