{"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/vl-t5","slug":"vl-t5","name":"VL-T5","full_name":"VL-T5","full_name_withheld":false,"description_markdown":"VL-T5 is a unified framework that learns different tasks in a single architecture with the same language modeling objective, i.e., multimodal conditional text generation. The model learns to generate labels in text based on the visual and textual inputs. In contrast to other existing methods, the framework unifies tasks as generating text labels conditioned on multimodal inputs. This allows the model to tackle vision-and-language tasks with unified text generation objective. The models use text prefixes to adapt to different tasks.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Unifying Vision-and-Language Tasks via Text Generation","paper":"/paper/unifying-vision-and-language-tasks-via-text","first_author":"Jaemin Cho","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/unifying-vision-and-language-tasks-via-text"},"source":{"url":"https://arxiv.org/abs/2102.02779v2","title":"Unifying Vision-and-Language Tasks via Text Generation","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":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"slug":"mixture-of-rationale-multi-modal-reasoning","title":"Mixture of Rationale: Multi-Modal Reasoning Mixture for Visual Question Answering","date":"2024-06-03","arxiv_id":"2406.01402","n_code_links":0,"syntology":null},{"paper":"/paper/visual-spatial-description-controlled-spatial","slug":"visual-spatial-description-controlled-spatial","title":"Visual Spatial Description: Controlled Spatial-Oriented Image-to-Text Generation","date":"2022-10-20","arxiv_id":"2210.11109","n_code_links":1,"syntology":null},{"paper":"/paper/webly-supervised-concept-expansion-for","slug":"webly-supervised-concept-expansion-for","title":"Webly Supervised Concept Expansion for General Purpose Vision Models","date":"2022-02-04","arxiv_id":"2202.02317","n_code_links":0,"syntology":null},{"paper":"/paper/vl-adapter-parameter-efficient-transfer","slug":"vl-adapter-parameter-efficient-transfer","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","date":"2021-12-13","arxiv_id":"2112.06825","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["ylsung/vl_adapter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","n_code_links":2,"syntology":{"ran":2,"of":12,"n_ran_checked":2,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}}],"papers_shown":5,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":5,"with_a_code_link":3,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/vl-t5/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/vl-t5/papers/ran/1","json":"/method/vl-t5/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/image-captioning","name":"Image Captioning","papers":3},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":3},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/referring-expression-comprehension","name":"Referring Expression Comprehension","papers":2},{"task":"/task/text-generation","name":"Text Generation","papers":2},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":2},{"task":"/task/conditional-text-generation","name":"Conditional Text Generation","papers":1},{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/human-object-interaction-detection","name":"Human-Object Interaction Detection","papers":1},{"task":null,"name":"Image Description","papers":1},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":1},{"task":"/task/image-to-text","name":"Image to text","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/multi-task-learning","name":"Multi-Task Learning","papers":1},{"task":"/task/object-categorization","name":"Object Categorization","papers":1},{"task":"/task/object-localization","name":"Object Localization","papers":1},{"task":"/task/referring-expression","name":"Referring Expression","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1}],"tasks_shown":20,"n_tasks":22,"usage_by_year":[{"year":"2021","papers":2},{"year":"2022","papers":2},{"year":"2024","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/vl-t5"},"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=VL-T5","read_at":"2026-10-05T01:03:44+00:00","query":"VL-T5","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2102.02779","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'VL-T5' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"748c1099ac1c321f1581cf57849e4fd28ca94e11e8d9a49bc2151f7c0ecf02a2","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}