{"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/oscar","slug":"oscar","name":"OSCAR","full_name":"OSCAR","full_name_withheld":false,"description_markdown":"OSCAR is a new learning method that uses object tags detected in images as anchor points to ease the learning of image-text alignment. The model take a triple as input (word-tag-region) and pre-trained with two losses (masked token loss over words and tags, and a contrastive loss between tags and others). OSCAR represents an image-text pair into semantic space via dictionary lookup. Object tags are used as anchor points to align image regions with word embeddings of pre-trained language models. The model is then fine-tuned for understanding and generation tasks.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","paper":"/paper/oscar-object-semantics-aligned-pre-training","first_author":"Xiujun Li","n_authors":12,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/oscar-object-semantics-aligned-pre-training"},"source":{"url":"https://arxiv.org/abs/2004.06165v5","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","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":36,"archive_num_papers":36,"papers_newest_first":[{"paper":"/paper/oscar-one-step-diffusion-codec-across","slug":"oscar-one-step-diffusion-codec-across","title":"OSCAR: One-Step Diffusion Codec for Image Compression Across Multiple Bit-rates","date":"2025-05-22","arxiv_id":"2505.16091","n_code_links":1,"syntology":null},{"paper":null,"slug":"oscar-online-soft-compression-and-reranking","title":"OSCAR: Online Soft Compression And Reranking","date":"2025-03-17","arxiv_id":"2504.07109","n_code_links":0,"syntology":null},{"paper":null,"slug":"oscar-object-status-and-contextual-awareness","title":"OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking","date":"2025-03-07","arxiv_id":"2503.05962","n_code_links":0,"syntology":null},{"paper":null,"slug":"one-shot-federated-learning-with-classifier-1","title":"One-Shot Federated Learning with Classifier-Free Diffusion Models","date":"2025-02-12","arxiv_id":"2502.08488","n_code_links":0,"syntology":null},{"paper":null,"slug":"longitudinal-abuse-and-sentiment-analysis-of","title":"Longitudinal Abuse and Sentiment Analysis of Hollywood Movie Dialogues using LLMs","date":"2025-01-20","arxiv_id":"2501.13948","n_code_links":0,"syntology":null},{"paper":null,"slug":"rephrasing-natural-text-data-with-different","title":"Rephrasing natural text data with different languages and quality levels for Large Language Model pre-training","date":"2024-10-28","arxiv_id":"2410.20796","n_code_links":0,"syntology":null},{"paper":null,"slug":"oscar-operating-system-control-via-state","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","date":"2024-10-24","arxiv_id":"2410.18963","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-fine-grained-webpage-fingerprinting","title":"Towards Fine-Grained Webpage Fingerprinting at Scale","date":"2024-09-06","arxiv_id":"2409.04341","n_code_links":0,"syntology":null},{"paper":null,"slug":"ikun-for-wmt24-general-mt-task-llms-are-here","title":"IKUN for WMT24 General MT Task: LLMs Are here for Multilingual Machine Translation","date":"2024-08-21","arxiv_id":"2408.11512","n_code_links":0,"syntology":null},{"paper":"/paper/tropical-expressivity-of-neural-networks","slug":"tropical-expressivity-of-neural-networks","title":"Tropical Expressivity of Neural Networks","date":"2024-05-30","arxiv_id":"2405.20174","n_code_links":1,"syntology":null},{"paper":"/paper/strong-screening-rules-for-group-based-slope","slug":"strong-screening-rules-for-group-based-slope","title":"Strong Screening Rules for Group-based SLOPE Models","date":"2024-05-24","arxiv_id":"2405.15357","n_code_links":1,"syntology":null},{"paper":null,"slug":"building-a-large-japanese-web-corpus-for","title":"Building a Large Japanese Web Corpus for Large Language Models","date":"2024-04-27","arxiv_id":"2404.17733","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-model-selection-for-generalized","title":"Automated Model Selection for Generalized Linear Models","date":"2024-04-25","arxiv_id":"2404.16560","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-language-models-care-about-text-quality","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","date":"2024-03-13","arxiv_id":"2403.08693","n_code_links":0,"syntology":null},{"paper":"/paper/oscar-object-state-captioning-and-state","slug":"oscar-object-state-captioning-and-state","title":"OSCaR: Object State Captioning and State Change Representation","date":"2024-02-27","arxiv_id":"2402.17128","n_code_links":1,"syntology":null},{"paper":"/paper/glotscript-a-resource-and-tool-for-low","slug":"glotscript-a-resource-and-tool-for-low","title":"GlotScript: A Resource and Tool for Low Resource Writing System Identification","date":"2023-09-23","arxiv_id":"2309.13320","n_code_links":1,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["cisnlp/GlotScript"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"paper":null,"slug":"pattern-recovery-in-penalized-and-thresholded","title":"A Unified Framework for Pattern Recovery in Penalized and Thresholded Estimation and its Geometry","date":"2023-07-19","arxiv_id":"2307.10158","n_code_links":0,"syntology":null},{"paper":"/paper/one-stage-cascade-refinement-networks-for","slug":"one-stage-cascade-refinement-networks-for","title":"One-Stage Cascade Refinement Networks for Infrared Small Target Detection","date":"2022-12-16","arxiv_id":"2212.08472","n_code_links":2,"syntology":null},{"paper":null,"slug":"robbert-2022-updating-a-dutch-language-model","title":"RobBERT-2022: Updating a Dutch Language Model to Account for Evolving Language Use","date":"2022-11-15","arxiv_id":"2211.08192","n_code_links":0,"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":null,"slug":"impact-of-tokenization-on-language-models-an-1","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2022-04-19","arxiv_id":"2204.08832","n_code_links":0,"syntology":null},{"paper":null,"slug":"wudaomm-a-large-scale-multi-modal-dataset-for","title":"WuDaoMM: A large-scale Multi-Modal Dataset for Pre-training models","date":"2022-03-22","arxiv_id":"2203.11480","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-cleaner-document-oriented","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","date":"2022-01-17","arxiv_id":"2201.06642","n_code_links":0,"syntology":null},{"paper":null,"slug":"impact-of-tokenization-on-language-models-an","title":"Impact of Tokenization on Language Models: An Analysis for Turkish","date":"2021-11-16","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pagnol-an-extra-large-french-generative-model","title":"PAGnol: An Extra-Large French Generative Model","date":"2021-10-16","arxiv_id":"2110.08554","n_code_links":0,"syntology":null},{"paper":"/paper/oscar-data-driven-operational-space-control","slug":"oscar-data-driven-operational-space-control","title":"OSCAR: Data-Driven Operational Space Control for Adaptive and Robust Robot Manipulation","date":"2021-10-02","arxiv_id":"2110.00704","n_code_links":1,"syntology":null},{"paper":null,"slug":"transliteration-a-simple-technique-for","title":"Transliteration: A Simple Technique For Improving Multilingual Language Modeling","date":"2021-09-29","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"a-thorough-review-on-recent-deep-learning","title":"A Thorough Review on Recent Deep Learning Methodologies for Image Captioning","date":"2021-07-28","arxiv_id":"2107.13114","n_code_links":0,"syntology":null},{"paper":"/paper/perception-matters-detecting-perception","slug":"perception-matters-detecting-perception","title":"Perception Matters: Detecting Perception Failures of VQA Models Using Metamorphic Testing","date":"2021-06-19","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/how-could-neural-networks-understand-programs","slug":"how-could-neural-networks-understand-programs","title":"How could Neural Networks understand Programs?","date":"2021-05-10","arxiv_id":"2105.04297","n_code_links":1,"syntology":null},{"paper":null,"slug":"quality-at-a-glance-an-audit-of-web-crawled","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","date":"2021-03-22","arxiv_id":"2103.12028","n_code_links":0,"syntology":null},{"paper":null,"slug":"gottbert-a-pure-german-language-model","title":"GottBERT: a pure German Language Model","date":"2020-12-03","arxiv_id":"2012.02110","n_code_links":0,"syntology":null},{"paper":"/paper/oscar-orthogonal-subspace-correction-and","slug":"oscar-orthogonal-subspace-correction-and","title":"OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings","date":"2020-06-30","arxiv_id":"2007.00049","n_code_links":1,"syntology":{"ran":10,"of":12,"n_ran_checked":9,"n_instrument":1,"unverified":2,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["Shaul1321/nullspace_projection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-path-algorithms-for-clustered-lasso","title":"Efficient Path Algorithms for Clustered Lasso and OSCAR","date":"2020-06-16","arxiv_id":"2006.08965","n_code_links":0,"syntology":null},{"paper":"/paper/a-monolingual-approach-to-contextualized-word","slug":"a-monolingual-approach-to-contextualized-word","title":"A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages","date":"2020-06-11","arxiv_id":"2006.06202","n_code_links":0,"syntology":null},{"paper":"/paper/oscar-object-semantics-aligned-pre-training","slug":"oscar-object-semantics-aligned-pre-training","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","date":"2020-04-13","arxiv_id":"2004.06165","n_code_links":4,"syntology":{"ran":13,"of":23,"n_ran_checked":10,"n_instrument":3,"unverified":10,"pointer_only":1,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified","official":{"repos":["microsoft/Oscar"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"papers_shown":36,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":36,"with_a_code_link":12,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":36,"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/oscar/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/oscar/papers/ran/1","json":"/method/oscar/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":5},{"task":"/task/language-modelling","name":"Language Modelling","papers":5},{"task":"/task/benchmarking","name":"Benchmarking","papers":3},{"task":"/task/image-captioning","name":"Image Captioning","papers":3},{"task":"/task/visual-question-answering","name":"Visual Question Answering (VQA)","papers":3},{"task":"/task/model","name":"model","papers":3},{"task":"/task/cg","name":"NER","papers":2},{"task":"/task/object","name":"Object","papers":2},{"task":"/task/question-answering","name":"Question Answering","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/word-embeddings","name":"Word Embeddings","papers":2},{"task":"/task/feature-selection","name":"feature selection","papers":2},{"task":"/task/regression-1","name":"regression","papers":2},{"task":"/task/caption-generation","name":"Caption Generation","papers":1},{"task":"/task/change-detection","name":"Change Detection","papers":1},{"task":"/task/clustering","name":"Clustering","papers":1},{"task":"/task/cross-modal-retrieval","name":"Cross-Modal Retrieval","papers":1},{"task":"/task/dnn-testing","name":"DNN Testing","papers":1},{"task":"/task/dataset-generation","name":"Dataset Generation","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1}],"tasks_shown":20,"n_tasks":55,"usage_by_year":[{"year":"2020","papers":5},{"year":"2021","papers":8},{"year":"2022","papers":6},{"year":"2023","papers":2},{"year":"2024","papers":10},{"year":"2025","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/oscar"},"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=OSCAR","read_at":"2026-10-05T00:59:56+00:00","query":"OSCAR","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":"OSCAR","origin_arxiv_id":"2609.24128"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2004.06165","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"listed_only"},"retrieve_with":null,"name_competition":{"verdict":"outranked","may_be_wrong_sense":true,"bearers_found":8,"served":{"arxiv_id":"2609.24128","citations":null},"leading_other_bearer":{"arxiv_id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","citations":2279,"named_by":["method_name","title_prefix"],"bearer_name":"Oscar","ask_with":"have('2004.06165')"},"n_other_bearers_listed":5,"note":"'OSCAR' is ALSO the name of the paper 'Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks' (arXiv:2004.06165, 2,279 citations), which is cited FAR more than the paper this answer is about (citations not recorded). This answer may be about the wrong OSCAR. If you meant the better-known one, ask again with that entry of `also_named`."},"name_competition_text":"The same name also belongs to “Oscar”, a method in the paper “Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks” (arXiv:2004.06165, 2,279 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name.","near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2609.24128","page":null,"syntology_url":"https://syntology.ai/paper/2609.24128","in_graph_layer":false,"samples":0},"line":"about another paper, arXiv:2609.24128: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: listed only). About another paper: this answer is about arXiv:2609.24128, while the archive credits arXiv:2004.06165.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"77f876dfec00d342bff5dfa89ab29da5733048639f6f736d8b1082221e7ee42d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}