Papers › Perceiver IO: A General Architecture for Structured Inputs & Outputs

Perceiver IO: A General Architecture for Structured Inputs & Outputs

30 Jul 2021ICLR 2022 4arXiv:2107.14795archive 2025-07-28

Andrew Jaegle, Sebastian Borgeaud, Jean-Baptiste Alayrac, Carl Doersch, Catalin Ionescu, David Ding, Skanda Koppula, Daniel Zoran, Andrew Brock, Evan Shelhamer, Olivier Hénaff, Matthew M. Botvinick, Andrew Zisserman, Oriol Vinyals, Joāo Carreira

A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs or outputs. In this work, we propose Perceiver IO, a general-purpose architecture that handles data from arbitrary settings while scaling linearly with the size of inputs and outputs. Our model augments the Perceiver with a flexible querying mechanism that enables outputs of various sizes and semantics, doing away with the need for task-specific architecture engineering. The same architecture achieves strong results on tasks spanning natural language and visual understanding, multi-task and multi-modal reasoning, and StarCraft II. As highlights, Perceiver IO outperforms a Transformer-based BERT baseline on the GLUE language benchmark despite removing input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation with no explicit mechanisms for multiscale correspondence.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2107.14795")

Code

Syntology Ran 7 of 11 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: community (archive-listed): 11 samples from 2 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

SforAiDl/vformer mentioned on GitHubpytorch report
esceptico/perceiver-io mentioned on GitHubpytorch report
huggingface/transformers mentioned on GitHubpytorch report
krasserm/perceiver-io mentioned on GitHubpytorchApache-2.0 report
lucidrains/perceiver-pytorch mentioned on GitHubpytorch 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

11 samples harvested; 7 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
4unverified

Licence: 0 of the 11 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Attention lucidrains/perceiver-pytorch/perceiver_pytorch/perceiver_io.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · cc13268d4214ea66 · report
CrossAttention esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) ran MIT (permissive) · cf3adb72e7c5e13d · report
FeedForward esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) ran MIT (permissive) · 649506f83d7c7ec5 · report
FeedForward lucidrains/perceiver-pytorch/perceiver_pytorch/perceiver_io.py community (archive-listed) ran · metamorphic tier: invariant MIT (permissive) · 2f461fda9e19682e · report
MultiHeadAttention esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) ran MIT (permissive) · 85192f7dbff6e0f1 · report
SelfAttention esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) ran MIT (permissive) · 0a3f8489bfe3c981 · report
dropout_seq lucidrains/perceiver-pytorch/perceiver_pytorch/perceiver_io.py community (archive-listed) ran MIT (permissive) · e54748ad3d6b3436 · report
BasePerceiverDecoder esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) unverified MIT (permissive) · 7ab6459dfe49fdd1 · report
PerceiverEncoder esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) unverified MIT (permissive) · b8273612dae53dd7 · report
PerceiverIO esceptico/perceiver-io/src/perceiver_io/perceiver.py community (archive-listed) unverified MIT (permissive) · 2fa5aec64645cecb · report
PerceiverIO lucidrains/perceiver-pytorch/perceiver_pytorch/perceiver_io.py community (archive-listed) unverified MIT (permissive) · 2a2bb9b0e4845046 · report

Tasks

Optical Flow EstimationStarcraftStarcraft II

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 Perceiver IO Average End-Point Error 4.98 #18 of 18 Archive leaderboard report
Optical Flow Estimation Sintel-clean Perceiver IO Average End-Point Error 1.81 #12 of 29 Archive leaderboard report
Optical Flow Estimation Sintel-final Perceiver IO Average End-Point Error 2.42 #4 of 28 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.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionPerceiver IOResidual ConnectionSoftmaxWeight DecayWordPiece

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