{"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/learning-to-learn-at-test-time","title":"Learning to (Learn at Test Time)","arxiv_id":"2310.13807","date":"2023-10-20","proceeding":null,"authors":["Yu Sun","Xinhao Li","Karan Dalal","Chloe Hsu","Sanmi Koyejo","Carlos Guestrin","Xiaolong Wang","Tatsunori Hashimoto","Xinlei Chen"],"abstract":"We reformulate the problem of supervised learning as learning to learn with two nested loops (i.e. learning problems). The inner loop learns on each individual instance with self-supervision before final prediction. The outer loop learns the self-supervised task used by the inner loop, such that its final prediction improves. Our inner loop turns out to be equivalent to linear attention when the inner-loop learner is only a linear model, and to self-attention when it is a kernel estimator. For practical comparison with linear or self-attention layers, we replace each of them in a transformer with an inner loop, so our outer loop is equivalent to training the architecture. When each inner-loop learner is a neural network, our approach vastly outperforms transformers with linear attention on ImageNet from 224 x 224 raw pixels in both accuracy and FLOPs, while (regular) transformers cannot run.","url_abs":"https://arxiv.org/abs/2310.13807v2","url_pdf":"https://arxiv.org/pdf/2310.13807v2.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":"learning-to-learn-at-test-time","repo_url":"https://github.com/test-time-training/mttt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.13807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.13807"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/test-time-training/mttt","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"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":"8fa1f6dea89abe40","entry":"blend","repo":"test-time-training/mttt","repo_kind":"official","path":"pp/autoaugment.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/pp/autoaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8fa1f6dea89abe40"}},{"code_sha256_prefix":"a1146beffdc1b587","entry":"cutout","repo":"test-time-training/mttt","repo_kind":"official","path":"pp/autoaugment.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/pp/autoaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a1146beffdc1b587"}},{"code_sha256_prefix":"f66ba180f0c3270b","entry":"get_posemb","repo":"test-time-training/mttt","repo_kind":"official","path":"model.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f66ba180f0c3270b"}},{"code_sha256_prefix":"7f6da8b96ca3fb1e","entry":"make_for_train","repo":"test-time-training/mttt","repo_kind":"official","path":"datasets/input_pipeline.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/datasets/input_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7f6da8b96ca3fb1e"}},{"code_sha256_prefix":"a9b79a3fcbad18af","entry":"posemb_sincos_2d","repo":"test-time-training/mttt","repo_kind":"official","path":"model.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a9b79a3fcbad18af"}},{"code_sha256_prefix":"2f023d4690a70195","entry":"solarize","repo":"test-time-training/mttt","repo_kind":"official","path":"pp/autoaugment.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/pp/autoaugment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f023d4690a70195"}},{"code_sha256_prefix":"474c43c3ad6f28e3","entry":"make_for_inference","repo":"test-time-training/mttt","repo_kind":"official","path":"datasets/input_pipeline.py","file_url":"https://github.com/test-time-training/mttt/blob/HEAD/datasets/input_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"474c43c3ad6f28e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}