{"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/xgpt","slug":"xgpt","name":"XGPT","full_name":"XGPT","full_name_withheld":false,"description_markdown":"XGPT is a method of cross-modal generative pre-training for image captioning designed to pre-train text-to-image caption generators through three novel generation tasks, including image-conditioned masked language modeling (IMLM), image-conditioned denoising autoencoding (IDA), and text-conditioned image feature generation (TIGF). The pre-trained XGPT can be fine-tuned without any task-specific architecture modifications and build strong image captioning models.","description_state":"present","introduced_year":null,"introduced_by":{"title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","paper":"/paper/xgpt-cross-modal-generative-pre-training-for","first_author":"Qiaolin Xia","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/xgpt-cross-modal-generative-pre-training-for"},"source":{"url":"https://arxiv.org/abs/2003.01473v2","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","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":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/xgpt-cross-modal-generative-pre-training-for","slug":"xgpt-cross-modal-generative-pre-training-for","title":"XGPT: Cross-modal Generative Pre-Training for Image Captioning","date":"2020-03-03","arxiv_id":"2003.01473","n_code_links":0,"syntology":null}],"papers_shown":1,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":1,"with_a_code_link":0,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":1,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"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":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[],"tasks":[{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":1},{"task":"/task/image-text-retrieval","name":"Image-text Retrieval","papers":1},{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/masked-language-modeling","name":"Masked Language Modeling","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":1},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":1}],"tasks_shown":11,"n_tasks":11,"usage_by_year":[{"year":"2020","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/xgpt"},"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=XGPT","read_at":"2026-10-05T01:04:00+00:00","query":"XGPT","kind":"paper","have":"no_code","tier":"paper_only","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2003.01473"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":"for_this_paper_only","absence_unchecked":null,"no_code_is_about_this_method":true,"subject":"same_paper","archive_paper_arxiv_id":"2003.01473","repositories":{"listed":null,"in_graph":0,"list_truncated":null,"strongest_link":null},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2003.01473","citations":84},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'XGPT'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2003.01473","page":"/paper/xgpt-cross-modal-generative-pre-training-for","syntology_url":"https://syntology.ai/paper/2003.01473","in_graph_layer":false,"samples":0},"line":"origin paper held, no code (paper_only). The lookup matched a paper by its title, arXiv:2003.01473, not a method entry. This answer is about arXiv:2003.01473, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7b541bd7f16852ab9dc60e01c9b299923e70ab900bc1e2d554dd289da823fcfb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}