{"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/lxmert","slug":"lxmert","name":"LXMERT","full_name":"Learning Cross-Modality Encoder Representations from Transformers","full_name_withheld":false,"description_markdown":"LXMERT is a model for learning vision-and-language cross-modality representations. It consists of a Transformer model that consists three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. The model takes two inputs: image with its related sentence. The images are represented as a sequence of objects, whereas each sentence is represented as sequence of words. By combining the self-attention and cross-attention layers the model is able to generated language representation, image representations, and cross-modality representations from the input. The model is pre-trained with image-sentence pairs via five pre-training tasks: masked language modeling, masked object prediction, cross-modality matching, and image questions answering. These tasks help the model to learn both intra-modality and cross-modality relationships.","description_state":"present","introduced_year":null,"introduced_by":{"title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","paper":"/paper/lxmert-learning-cross-modality-encoder","first_author":"Hao Tan","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/lxmert-learning-cross-modality-encoder"},"source":{"url":"https://arxiv.org/abs/1908.07490v3","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","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":40,"archive_num_papers":40,"papers_newest_first":[{"paper":null,"slug":"optimizing-visual-question-answering-models","title":"Optimizing Visual Question Answering Models for Driving: Bridging the Gap Between Human and Machine Attention Patterns","date":"2024-06-13","arxiv_id":"2406.09203","n_code_links":0,"syntology":null},{"paper":"/paper/beyond-image-text-matching-verb-understanding","slug":"beyond-image-text-matching-verb-understanding","title":"Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking","date":"2024-01-29","arxiv_id":"2401.16575","n_code_links":1,"syntology":null},{"paper":"/paper/lxmert-model-compression-for-visual-question","slug":"lxmert-model-compression-for-visual-question","title":"LXMERT Model Compression for Visual Question Answering","date":"2023-10-23","arxiv_id":"2310.15325","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-grounded-visual-spatial-reasoning-in","title":"Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models","date":"2023-08-18","arxiv_id":"2308.09778","n_code_links":0,"syntology":null},{"paper":"/paper/towards-a-performance-analysis-on-pre-trained","slug":"towards-a-performance-analysis-on-pre-trained","title":"Towards a performance analysis on pre-trained Visual Question Answering models for autonomous driving","date":"2023-07-18","arxiv_id":"2307.09329","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-the-language-modal-in","title":"An Empirical Study on the Language Modal in Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10143","n_code_links":0,"syntology":null},{"paper":null,"slug":"probing-the-role-of-positional-information-in-2","title":"Probing the Role of Positional Information in Vision-Language Models","date":"2023-05-17","arxiv_id":"2305.10046","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/mm-shap-a-performance-agnostic-metric-for","slug":"mm-shap-a-performance-agnostic-metric-for","title":"MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks","date":"2022-12-15","arxiv_id":"2212.08158","n_code_links":1,"syntology":{"ran":5,"of":10,"n_ran_checked":5,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["heidelberg-nlp/mm-shap"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-self-consistency-and-performance-of","title":"Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference","date":"2022-11-21","arxiv_id":"2211.11875","n_code_links":0,"syntology":null},{"paper":"/paper/compressing-and-debiasing-vision-language-pre","slug":"compressing-and-debiasing-vision-language-pre","title":"Compressing And Debiasing Vision-Language Pre-Trained Models for Visual Question Answering","date":"2022-10-26","arxiv_id":"2210.14558","n_code_links":1,"syntology":null},{"paper":null,"slug":"probing-cross-modal-semantics-alignment","title":"Probing Cross-modal Semantics Alignment Capability from the Textual Perspective","date":"2022-10-18","arxiv_id":"2210.09550","n_code_links":0,"syntology":null},{"paper":"/paper/generative-bias-for-visual-question-answering","slug":"generative-bias-for-visual-question-answering","title":"Generative Bias for Robust Visual Question Answering","date":"2022-08-01","arxiv_id":"2208.00690","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 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) · 0 unverified","official":{"repos":["chojw/genb"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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":null,"slug":"visio-linguistic-brain-encoding-1","title":"Visio-Linguistic Brain Encoding","date":"2022-04-18","arxiv_id":"2204.08261","n_code_links":0,"syntology":null},{"paper":"/paper/swapmix-diagnosing-and-regularizing-the-over","slug":"swapmix-diagnosing-and-regularizing-the-over","title":"SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering","date":"2022-04-05","arxiv_id":"2204.02285","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-multi-modal-representations-for","slug":"exploring-multi-modal-representations-for","title":"Exploring Multi-Modal Representations for Ambiguity Detection & Coreference Resolution in the SIMMC 2.0 Challenge","date":"2022-02-25","arxiv_id":"2202.12645","n_code_links":2,"syntology":null},{"paper":null,"slug":"probing-the-role-of-positional-information-in","title":"Probing the Role of Positional Information in Vision-Language Models","date":"2022-01-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-learning-are-captions-all-you-need","title":"Multimodal Learning: Are Captions All You Need?","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"region-under-discussion-for-visual-dialog","title":"Region under Discussion for visual dialog","date":"2021-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-things-or-seeing-scenes-investigating","title":"Seeing things or seeing scenes: Investigating the capabilities of V&L models to align scene descriptions to images","date":"2021-10-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dense-contrastive-visual-linguistic","title":"Dense Contrastive Visual-Linguistic Pretraining","date":"2021-09-24","arxiv_id":"2109.11778","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-vision-language-models-see-when-they-see","title":"What Vision-Language Models `See' when they See Scenes","date":"2021-09-15","arxiv_id":"2109.07301","n_code_links":0,"syntology":null},{"paper":"/paper/data-efficient-masked-language-modeling-for","slug":"data-efficient-masked-language-modeling-for","title":"Data Efficient Masked Language Modeling for Vision and Language","date":"2021-09-05","arxiv_id":"2109.02040","n_code_links":1,"syntology":null},{"paper":"/paper/learning-to-read-maps-understanding-natural","slug":"learning-to-read-maps-understanding-natural","title":"Learning to Read Maps: Understanding Natural Language Instructions from Unseen Maps","date":"2021-08-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/multi-stage-pre-training-over-simplified","slug":"multi-stage-pre-training-over-simplified","title":"Multi-stage Pre-training over Simplified Multimodal Pre-training Models","date":"2021-07-22","arxiv_id":"2107.14596","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":9,"phrase":"3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","official":{"repos":["lttsmn/LXMERT-S"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/passage-retrieval-for-outside-knowledge","slug":"passage-retrieval-for-outside-knowledge","title":"Passage Retrieval for Outside-Knowledge Visual Question Answering","date":"2021-05-09","arxiv_id":"2105.03938","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["prdwb/okvqa-release"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"chop-chop-bert-visual-question-answering-by","title":"Chop Chop BERT: Visual Question Answering by Chopping VisualBERT's Heads","date":"2021-04-30","arxiv_id":"2104.14741","n_code_links":0,"syntology":null},{"paper":null,"slug":"playing-lottery-tickets-with-vision-and","title":"Playing Lottery Tickets with Vision and Language","date":"2021-04-23","arxiv_id":"2104.11832","n_code_links":0,"syntology":null},{"paper":null,"slug":"analysis-on-image-set-visual-question","title":"Analysis on Image Set Visual Question Answering","date":"2021-03-31","arxiv_id":"2104.00107","n_code_links":0,"syntology":null},{"paper":null,"slug":"visual-grounding-strategies-for-text-only","title":"Visual Grounding Strategies for Text-Only Natural Language Processing","date":"2021-03-25","arxiv_id":"2103.13942","n_code_links":0,"syntology":null},{"paper":"/paper/seeing-past-words-testing-the-cross-modal","slug":"seeing-past-words-testing-the-cross-modal","title":"Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks","date":"2020-12-22","arxiv_id":"2012.12352","n_code_links":0,"syntology":null},{"paper":null,"slug":"they-are-not-all-alike-answering-different","title":"They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies","date":"2020-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","n_code_links":2,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"1 ran (of which 0 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) · 1 unverified","official":{"repos":["allenai/x-lxmert"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/a-comparison-of-pre-trained-vision-and","slug":"a-comparison-of-pre-trained-vision-and","title":"A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports","date":"2020-09-03","arxiv_id":"2009.01523","n_code_links":1,"syntology":null},{"paper":null,"slug":"contrastive-visual-linguistic-pretraining","title":"Contrastive Visual-Linguistic Pretraining","date":"2020-07-26","arxiv_id":"2007.13135","n_code_links":0,"syntology":null},{"paper":null,"slug":"what-does-bert-with-vision-look-at","title":"What Does BERT with Vision Look At?","date":"2020-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"behind-the-scene-revealing-the-secrets-of-pre","title":"Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models","date":"2020-05-15","arxiv_id":"2005.07310","n_code_links":0,"syntology":null},{"paper":"/paper/lxmert-learning-cross-modality-encoder","slug":"lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","arxiv_id":"1908.07490","n_code_links":9,"syntology":{"ran":4,"of":15,"n_ran_checked":4,"n_instrument":0,"unverified":11,"pointer_only":3,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","official":{"repos":["airsplay/lxmert"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":40,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":40,"with_a_code_link":17,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":40,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":7,"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":7,"papers_where_code_ran_first_page":"/method/lxmert/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/lxmert/papers/ran/1","json":"/method/lxmert/papers/ran/1.json","rows":7}],"tasks":[{"task":"/task/question-answering","name":"Question Answering","papers":18},{"task":"/task/visual-question-answering-1","name":"Visual Question Answering","papers":18},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":18},{"task":"/task/language-modeling","name":"Language Modeling","papers":5},{"task":"/task/language-modelling","name":"Language Modelling","papers":5},{"task":"/task/retrieval","name":"Retrieval","papers":5},{"task":"/task/sentence","name":"Sentence","papers":5},{"task":"/task/contrastive-learning","name":"Contrastive Learning","papers":4},{"task":"/task/image-captioning","name":"Image Captioning","papers":4},{"task":"/task/image-text-matching","name":"Image-text matching","papers":4},{"task":"/task/text-matching","name":"Text Matching","papers":4},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":4},{"task":"/task/image-text-retrieval","name":"Image-text Retrieval","papers":3},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/object-localization","name":"Object Localization","papers":3},{"task":"/task/representation-learning","name":"Representation Learning","papers":3},{"task":"/task/text-retrieval","name":"Text Retrieval","papers":3},{"task":"/task/all","name":"All","papers":2},{"task":"/task/autonomous-driving","name":"Autonomous Driving","papers":2},{"task":"/task/coreference-resolution","name":"Coreference Resolution","papers":2}],"tasks_shown":20,"n_tasks":44,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":7},{"year":"2021","papers":13},{"year":"2022","papers":11},{"year":"2023","papers":6},{"year":"2024","papers":2}],"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/lxmert"},"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=LXMERT","read_at":"2026-10-05T00:58:49+00:00","query":"LXMERT","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":"LXMERT","origin_arxiv_id":"1908.07490"},"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":"1908.07490","repositories":{"listed":5,"in_graph":9,"list_truncated":true,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"1908.07490","citations":3011},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'LXMERT'. 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":"1908.07490","page":"/paper/lxmert-learning-cross-modality-encoder","syntology_url":"https://syntology.ai/paper/1908.07490","in_graph_layer":true,"samples":15,"ran":4,"n_ran_checked":4,"n_instrument":0,"unverified":11,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified; every one of the 4 samples 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 9 in the graph, strongest link: official). This answer is about arXiv:1908.07490, the paper the archive credits with this method.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"18ca8ab93007ae521bf47036aa043ce10488a8b8f01ce731ee8940e2e9bb71cb","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}