{"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":"/method/vilt","slug":"vilt","name":"ViLT","full_name":"Vision-and-Language Transformer","full_name_withheld":false,"description_markdown":"ViLT is a minimal vision-and-language pre-training transformer model where processing of visual inputs is simplified to just the same convolution-free manner that text inputs are processed. The model-specific components of ViLT require less computation than the transformer component for multimodal interactions. ViLTThe model is pre-trained on the following objectives: image text matching, masked language modeling, and word patch alignment.","description_state":"present","introduced_year":null,"introduced_by":{"title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","paper":"/paper/vilt-vision-and-language-transformer-without","first_author":"Wonjae Kim","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/vilt-vision-and-language-transformer-without"},"source":{"url":"https://arxiv.org/abs/2102.03334v2","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Vision and Language Pre-Trained Models","url":"/methods/category/vision-and-language-pre-trained-models","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"slug":"seeing-more-with-less-human-like","title":"Seeing More with Less: Human-like Representations in Vision Models","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/visual-robustness-benchmark-for-visual","slug":"visual-robustness-benchmark-for-visual","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","date":"2024-07-03","arxiv_id":"2407.03386","n_code_links":1,"syntology":null},{"paper":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/vl-checklist-evaluating-pre-trained-vision","slug":"vl-checklist-evaluating-pre-trained-vision","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","date":"2022-07-01","arxiv_id":"2207.00221","n_code_links":1,"syntology":null},{"paper":"/paper/visual-spatial-reasoning","slug":"visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","arxiv_id":"2205.00363","n_code_links":4,"syntology":{"ran":7,"of":10,"n_ran_checked":5,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["cambridgeltl/visual-spatial-reasoning","sohojoe/clip_visual-spatial-reasoning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","n_code_links":6,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}}],"papers_shown":6,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":6,"with_a_code_link":5,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/method/vilt/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/vilt/papers/ran/1","json":"/method/vilt/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":3},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":3},{"task":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval","papers":2},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":2},{"task":"/task/zero-shot-cross-modal-retrieval","name":"Zero-Shot Cross-Modal Retrieval","papers":2},{"task":"/task/object-detection-1","name":"object-detection","papers":2},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/multimodal-intent-recognition","name":"Multimodal Intent Recognition","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/object-detection","name":"Object Detection","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/spatial-reasoning","name":"Spatial Reasoning","papers":1},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":1},{"task":"/task/visual-entailment","name":"Visual Entailment","papers":1},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":1},{"task":"/task/zero-shot-visual-question-answring","name":"Zero-Shot Visual Question Answring","papers":1},{"task":"/task/multimodal-interaction","name":"multimodal interaction","papers":1}],"tasks_shown":17,"n_tasks":17,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":2},{"year":"2023","papers":1},{"year":"2024","papers":1},{"year":"2025","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/vilt"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=ViLT","read_at":"2026-10-05T01:03:40+00:00","query":"ViLT","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"ViLT","origin_arxiv_id":"2102.03334"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2102.03334","repositories":{"listed":5,"in_graph":6,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"contested","may_be_wrong_sense":false,"bearers_found":2,"served":{"arxiv_id":"2102.03334","citations":2401},"leading_other_bearer":{"arxiv_id":"2208.10858","title":"VILT: Video Instructions Linking for Complex Tasks","citations":null,"named_by":["title_prefix"],"bearer_name":"VILT: Video Instructions Linking for Complex Tasks","ask_with":"have('2208.10858')"},"n_other_bearers_listed":1,"note":"1 other thing(s) here are also called 'ViLT', and none of them is cited more than the paper this answer is about. They are listed in `also_named` -- check `served.arxiv_id` is the paper you meant."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2102.03334","page":"/paper/vilt-vision-and-language-transformer-without","syntology_url":"https://syntology.ai/paper/2102.03334","in_graph_layer":true,"samples":4,"ran":1,"n_ran_checked":1,"n_instrument":0,"unverified":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; the one sample that ran constructed an object rather than computing a result","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"repository known, no verified implementation (declared_code; repositories: 5 listed of 6 in the graph, strongest link: official). This answer is about arXiv:2102.03334, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"5906d5f284cbd344a74cc22f262e0b6bd4b40ad0afea146bed298c0c1fa20945","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}