{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/eva-clip-improved-training-techniques-for","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","arxiv_id":"2303.15389","date":"2023-03-27","proceeding":null,"authors":["Quan Sun","Yuxin Fang","Ledell Wu","Xinlong Wang","Yue Cao"],"abstract":"Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models that significantly improve the efficiency and effectiveness of CLIP training. Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs. Notably, our largest 5.0B-parameter EVA-02-CLIP-E/14+ with only 9 billion seen samples achieves 82.0 zero-shot top-1 accuracy on ImageNet-1K val. A smaller EVA-02-CLIP-L/14+ with only 430 million parameters and 6 billion seen samples achieves 80.4 zero-shot top-1 accuracy on ImageNet-1K val. To facilitate open access and open research, we release the complete suite of EVA-CLIP to the community at https://github.com/baaivision/EVA/tree/master/EVA-CLIP.","url_abs":"https://arxiv.org/abs/2303.15389v1","url_pdf":"https://arxiv.org/pdf/2303.15389v1.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":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/baaivision/eva","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/Yui010206/CREMA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/jaehong31/raccoon","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"eva-clip-improved-training-techniques-for","repo_url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-transfer-image-classification","task_name":"Zero-Shot Transfer Image Classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-objectnet","task":"Image Classification","dataset":"ObjectNet","model":"EVA-02-CLIP-E/14+","rank_in_archive_order":4,"of":106,"metrics":{"Top-1 Accuracy":"79.6"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-action-recognition-on-ucf101","task":"Zero-Shot Action Recognition","dataset":"UCF101","model":"EVA-CLIP-E/14+","rank_in_archive_order":8,"of":35,"metrics":{"Top-1 Accuracy":"83.1"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-17","task":"Zero-Shot Transfer Image Classification","dataset":"Food-101","model":"EVA-CLIP-E/14+","rank_in_archive_order":4,"of":5,"metrics":{"Top 1 Accuracy":"94.9"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-1","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet","model":"EVA-CLIP-E/14+","rank_in_archive_order":12,"of":23,"metrics":{"Accuracy (Private)":"82"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-3","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet V2","model":"EVA-CLIP-E/14+","rank_in_archive_order":9,"of":13,"metrics":{"Accuracy (Private)":"75.7"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-5","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-A","model":"EVA-CLIP-E/14+","rank_in_archive_order":8,"of":13,"metrics":{"Accuracy (Private)":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-4","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-R","model":"EVA-CLIP-E/14+","rank_in_archive_order":7,"of":12,"metrics":{"Accuracy":"94.5"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-8","task":"Zero-Shot Transfer Image Classification","dataset":"ImageNet-Sketch","model":"EVA-CLIP-E/14+","rank_in_archive_order":6,"of":7,"metrics":{"Accuracy (Private)":"71.6"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-transfer-image-classification-on-6","task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","model":"EVA-CLIP-E/14+","rank_in_archive_order":7,"of":9,"metrics":{"Accuracy (Private)":"79.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2303.15389","atlas_url":"https://app.syntology.ai/?focus=2303.15389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15389"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.15389"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2303.15389"},"call":"get_harvested_code_for_paper(arxiv_id=\"2303.15389\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2303.15389"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2303.15389\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2303.15389"},"call":"get_concepts_for_paper(arxiv_id=\"2303.15389\")"}],"by_repo":[{"repo":"baaivision/eva","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["2211.07636","2402.04252"],"harvested_for_calls":[{"arxiv_id":"2211.07636","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2211.07636"},"call":"get_harvested_code_for_paper(arxiv_id=\"2211.07636\")"},{"arxiv_id":"2402.04252","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.04252"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.04252\")"}]},{"repo":"Yui010206/CREMA","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2402.05889"],"harvested_for_calls":[{"arxiv_id":"2402.05889","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2402.05889"},"call":"get_harvested_code_for_paper(arxiv_id=\"2402.05889\")"}]},{"repo":"jaehong31/raccoon","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2405.18406"],"harvested_for_calls":[{"arxiv_id":"2405.18406","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2405.18406"},"call":"get_harvested_code_for_paper(arxiv_id=\"2405.18406\")"}]},{"repo":"PaddlePaddle/PaddleMIX","kind":"listed","samples":4,"ran":1,"instrument":0,"unverified":3}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2303.15389.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2303.15389.svg"},"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/Yui010206/CREMA","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baaivision/eva","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaehong31/raccoon","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples","reach":null}],"summary":{"ran":1,"unverified":3},"n_samples":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":4,"ran":1,"n_ran_checked":1,"n_instrument":0,"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"},"official_not_harvested":{"repositories":["baaivision/eva"],"harvested_for_other_papers":[2],"samples_from_other_repositories":4,"other_repositories":1,"samples_unlocated":0},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"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_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":1,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"00373b30be1d98cd","code_sha256_prefix":"00373b30be1d98cd","entry":"create_ui","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/interface.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/interface.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"fixture_out_type":"Blocks","level_recorded_at":"2026-09-24T22:55:07.240920+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"00373b30be1d98cd"}},{"code_sha256":"f523f7dc0633013b","code_sha256_prefix":"f523f7dc0633013b","entry":"get_model_info","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-model-info","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f523f7dc0633013b"}},{"code_sha256":"ac470b0ec166399d","code_sha256_prefix":"ac470b0ec166399d","entry":"get_model_path","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-model-path","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"ac470b0ec166399d"}},{"code_sha256":"903eaa561fc807bb","code_sha256_prefix":"903eaa561fc807bb","entry":"get_template","repo":"PaddlePaddle/PaddleMIX","repo_kind":"listed","path":"paddlemix/MULLM_WebUI/common.py","file_url":"https://github.com/PaddlePaddle/PaddleMIX/blob/HEAD/paddlemix/MULLM_WebUI/common.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-template","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"903eaa561fc807bb"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"35c2704ddfd7db5ed86ce1e6a0906cda98e07332cc37165e99d0fab83605dc63","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}