{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/perceiver-io-a-general-architecture-for","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","arxiv_id":"2107.14795","date":"2021-07-30","proceeding":"ICLR 2022 4","authors":["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"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2107.14795v3","url_pdf":"https://arxiv.org/pdf/2107.14795v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/deepmind/deepmind-research/tree/master/perceiver","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/SforAiDl/vformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/esceptico/perceiver-io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/krasserm/perceiver-io","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/lucidrains/perceiver-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/2796gaurav/code_examples/tree/main/Perceiver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/MindCode-4/code-2/tree/main/perceiver","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"perceiver-io-a-general-architecture-for","repo_url":"https://github.com/MindSpore-scientific-2/code-7/tree/main/SISDTA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"starcraft","task_name":"Starcraft"},{"task_slug":"starcraft-ii","task_name":"Starcraft II"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"perceiver-io","method_name":"Perceiver IO"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/optical-flow-estimation-on-kitti-2015","task":"Optical Flow Estimation","dataset":"KITTI 2015","model":"Perceiver IO","rank_in_archive_order":18,"of":18,"metrics":{"Average End-Point Error":"4.98"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-clean","task":"Optical Flow Estimation","dataset":"Sintel-clean","model":"Perceiver IO","rank_in_archive_order":12,"of":29,"metrics":{"Average End-Point Error":"1.81"},"uses_additional_data":false},{"leaderboard":"/sota/optical-flow-estimation-on-sintel-final","task":"Optical Flow Estimation","dataset":"Sintel-final","model":"Perceiver IO","rank_in_archive_order":4,"of":28,"metrics":{"Average End-Point Error":"2.42"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.14795","atlas_url":"https://app.syntology.ai/?focus=2107.14795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.14795"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-7/tree/main/SISDTA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-2/tree/main/perceiver","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/perceiver-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/esceptico/perceiver-io","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepmind/deepmind-research/tree/master/perceiver","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SforAiDl/vformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2796gaurav/code_examples/tree/main/Perceiver","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/krasserm/perceiver-io","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":11,"ran":7,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"cc13268d4214ea66","entry":"Attention","repo":"lucidrains/perceiver-pytorch","repo_kind":"listed","path":"perceiver_pytorch/perceiver_io.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_io.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc13268d4214ea66"}},{"code_sha256_prefix":"cf3adb72e7c5e13d","entry":"CrossAttention","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cf3adb72e7c5e13d"}},{"code_sha256_prefix":"649506f83d7c7ec5","entry":"FeedForward","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"649506f83d7c7ec5"}},{"code_sha256_prefix":"2f461fda9e19682e","entry":"FeedForward","repo":"lucidrains/perceiver-pytorch","repo_kind":"listed","path":"perceiver_pytorch/perceiver_io.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_io.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f461fda9e19682e"}},{"code_sha256_prefix":"85192f7dbff6e0f1","entry":"MultiHeadAttention","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"85192f7dbff6e0f1"}},{"code_sha256_prefix":"0a3f8489bfe3c981","entry":"SelfAttention","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0a3f8489bfe3c981"}},{"code_sha256_prefix":"e54748ad3d6b3436","entry":"dropout_seq","repo":"lucidrains/perceiver-pytorch","repo_kind":"listed","path":"perceiver_pytorch/perceiver_io.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_io.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e54748ad3d6b3436"}},{"code_sha256_prefix":"7ab6459dfe49fdd1","entry":"BasePerceiverDecoder","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7ab6459dfe49fdd1"}},{"code_sha256_prefix":"b8273612dae53dd7","entry":"PerceiverEncoder","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8273612dae53dd7"}},{"code_sha256_prefix":"2fa5aec64645cecb","entry":"PerceiverIO","repo":"esceptico/perceiver-io","repo_kind":"listed","path":"src/perceiver_io/perceiver.py","file_url":"https://github.com/esceptico/perceiver-io/blob/HEAD/src/perceiver_io/perceiver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fa5aec64645cecb"}},{"code_sha256_prefix":"2a2bb9b0e4845046","entry":"PerceiverIO","repo":"lucidrains/perceiver-pytorch","repo_kind":"listed","path":"perceiver_pytorch/perceiver_io.py","file_url":"https://github.com/lucidrains/perceiver-pytorch/blob/HEAD/perceiver_pytorch/perceiver_io.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a2bb9b0e4845046"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}