{"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/flava","slug":"flava","name":"FLAVA","full_name":"FLAVA","full_name_withheld":false,"description_markdown":"FLAVA aims at building a single holistic universal model that targets all modalities at once. FLAVA is a language vision alignment model that learns strong representations from multimodal data (image-text pairs) and unimodal data (unpaired images and text). The model consists of an image encode transformer to capture unimodal image representations, a text encoder transformer to process unimodal text information, and a multimodal encode transformer that takes as input the encoded unimodal image and text and integrates their representations for multimodal reasoning. During pretraining, masked image modeling (MIM) and mask language modeling (MLM) losses are applied onto the image and text encoders over a single image or a text piece, respectively, while contrastive, masked multimodal modeling (MMM), and image-text matching (ITM) loss are used over paired image-text data. For downstream tasks, classification heads are applied on the outputs from the image, text, and multimodal encoders respectively for visual recognition, language understanding, and multimodal reasoning tasks It can be applied to broad scope of tasks from three domains (visual recognition, language understanding, and multimodal reasoning) under a common transformer model architecture.","description_state":"present","introduced_year":null,"introduced_by":{"title":"FLAVA: A Foundational Language And Vision Alignment Model","paper":"/paper/flava-a-foundational-language-and-vision","first_author":"Amanpreet Singh","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/flava-a-foundational-language-and-vision"},"source":{"url":"https://arxiv.org/abs/2112.04482v3","title":"FLAVA: A Foundational Language And Vision Alignment Model","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":11,"archive_num_papers":11,"papers_newest_first":[{"paper":null,"slug":"the-age-of-spiritual-machines-language","title":"The age of spiritual machines: Language quietus induces synthetic altered states of consciousness in artificial intelligence","date":"2024-09-30","arxiv_id":"2410.00257","n_code_links":0,"syntology":null},{"paper":null,"slug":"ospc-detecting-harmful-memes-with-large","title":"OSPC: Detecting Harmful Memes with Large Language Model as a Catalyst","date":"2024-06-14","arxiv_id":"2406.09779","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-structured-are-the-representations-in","title":"Interpreting the structure of multi-object representations in vision encoders","date":"2024-06-13","arxiv_id":"2406.09067","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-linguistic-knowledge-from","title":"Acquiring Linguistic Knowledge from Multimodal Input","date":"2024-02-27","arxiv_id":"2402.17936","n_code_links":0,"syntology":null},{"paper":null,"slug":"aigen-foodreview-a-multimodal-dataset-of","title":"AiGen-FoodReview: A Multimodal Dataset of Machine-Generated Restaurant Reviews and Images on Social Media","date":"2024-01-16","arxiv_id":"2401.08825","n_code_links":0,"syntology":null},{"paper":"/paper/whisbert-multimodal-text-audio-language","slug":"whisbert-multimodal-text-audio-language","title":"WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words","date":"2023-12-05","arxiv_id":"2312.02931","n_code_links":1,"syntology":null},{"paper":null,"slug":"lifelong-audio-video-masked-autoencoder-with","title":"STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment","date":"2023-10-12","arxiv_id":"2310.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"momo-a-shared-encoder-model-for-text-image","title":"MoMo: A shared encoder Model for text, image and multi-Modal representations","date":"2023-04-11","arxiv_id":"2304.05523","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-for-stereotypes-in-multimodal","title":"Controlling for Stereotypes in Multimodal Language Model Evaluation","date":"2023-02-03","arxiv_id":"2302.01582","n_code_links":0,"syntology":null},{"paper":"/paper/vl-taboo-an-analysis-of-attribute-based-zero","slug":"vl-taboo-an-analysis-of-attribute-based-zero","title":"VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models","date":"2022-09-12","arxiv_id":"2209.06103","n_code_links":1,"syntology":null},{"paper":"/paper/flava-a-foundational-language-and-vision","slug":"flava-a-foundational-language-and-vision","title":"FLAVA: A Foundational Language And Vision Alignment Model","date":"2021-12-08","arxiv_id":"2112.04482","n_code_links":4,"syntology":null}],"papers_shown":11,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":11,"with_a_code_link":3,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":11,"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/language-modelling","name":"Language Modelling","papers":4},{"task":"/task/language-modeling","name":"Language Modeling","papers":3},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/continual-learning","name":"Continual Learning","papers":1},{"task":"/task/decision-making","name":"Decision Making","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/image-to-text-retrieval","name":"Image-to-Text Retrieval","papers":1},{"task":"/task/language-model-evaluation","name":"Language Model Evaluation","papers":1},{"task":"/task/large-language-model","name":"Large Language Model","papers":1},{"task":"/task/object","name":"Object","papers":1},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition","papers":1},{"task":"/task/optical-character-recognition","name":"Optical Character Recognition (OCR)","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":1},{"task":"/task/unity","name":"Unity","papers":1},{"task":"/task/video-alignment","name":"Video Alignment","papers":1},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":1}],"tasks_shown":20,"n_tasks":25,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":4},{"year":"2024","papers":5}],"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/flava"},"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=FLAVA","read_at":"2026-10-05T00:56:03+00:00","query":"FLAVA","kind":"paper","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":"2112.04482","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":3,"served":null,"leading_other_bearer":{"arxiv_id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","citations":1005,"named_by":["title_prefix"],"bearer_name":"FLAVA: A Foundational Language And Vision Alignment Model","ask_with":"have('2112.04482')"},"n_other_bearers_listed":3,"note":"Nothing resolved to 'FLAVA' by name, but 3 thing(s) here DECLARE that name -- most cited: the paper 'FLAVA: A Foundational Language And Vision Alignment Model' (arXiv:2112.04482, 1,005 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 3 entries in Syntology's graph carry it; the most cited is the paper “FLAVA: A Foundational Language And Vision Alignment Model” (arXiv:2112.04482, 1,005 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"8def7097322f895b85ed6d04124245ac6f06a06a42fe500c1db85f8b97987e01","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}