{"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":"/task/image-to-text/papers/ran/1","list_of":"/task/image-to-text","task":"Image to text","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":1,"rows_per_page":100,"rows":[1,33],"of":33,"counts":{"archive_papers_tagged":246,"with_a_code_link":103,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":246,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":3,"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"},"first_page":"/task/image-to-text/papers/ran/1","prev":null,"next":null,"papers":[{"url":"/paper/flowtok-flowing-seamlessly-across-text-and","slug":"flowtok-flowing-seamlessly-across-text-and","title":"FlowTok: Flowing Seamlessly Across Text and Image Tokens","date":"2025-03-13","arxiv_id":"2503.10772","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/flowtok-flowing-seamlessly-across-text-and#ran","syntology_url":"https://syntology.ai/paper/2503.10772","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10772"}},"official":{"repos":["bytedance/1d-tokenizer"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/doracycle-domain-oriented-adaptation-of","slug":"doracycle-domain-oriented-adaptation-of","title":"DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles","date":"2025-03-05","arxiv_id":"2503.03651","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/doracycle-domain-oriented-adaptation-of#ran","syntology_url":"https://syntology.ai/paper/2503.03651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03651"}},"official":{"repos":["showlab/doracycle"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/magma-a-foundation-model-for-multimodal-ai","slug":"magma-a-foundation-model-for-multimodal-ai","title":"Magma: A Foundation Model for Multimodal AI Agents","date":"2025-02-18","arxiv_id":"2502.13130","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/magma-a-foundation-model-for-multimodal-ai#ran","syntology_url":"https://syntology.ai/paper/2502.13130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.13130"}},"official":{"repos":["microsoft/Magma"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/generalizing-from-simple-to-hard-visual","slug":"generalizing-from-simple-to-hard-visual","title":"Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?","date":"2025-01-05","arxiv_id":"2501.02669","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalizing-from-simple-to-hard-visual#ran","syntology_url":"https://syntology.ai/paper/2501.02669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.02669"}},"official":{"repos":["princeton-pli/vlm_s2h"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/revealing-and-reducing-gender-biases-in","slug":"revealing-and-reducing-gender-biases-in","title":"Revealing and Reducing Gender Biases in Vision and Language Assistants (VLAs)","date":"2024-10-25","arxiv_id":"2410.19314","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/revealing-and-reducing-gender-biases-in#ran","syntology_url":"https://syntology.ai/paper/2410.19314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19314"}},"official":{"repos":["explainableml/vla-gender-bias"],"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":["official"]}}},{"url":"/paper/unifashion-a-unified-vision-language-model","slug":"unifashion-a-unified-vision-language-model","title":"UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation","date":"2024-08-21","arxiv_id":"2408.11305","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":11,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/unifashion-a-unified-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2408.11305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11305"}},"official":{"repos":["xiangyu-mm/unifashion"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/contrasting-deepfakes-diffusion-via","slug":"contrasting-deepfakes-diffusion-via","title":"Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities","date":"2024-07-29","arxiv_id":"2407.20337","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/contrasting-deepfakes-diffusion-via#ran","syntology_url":"https://syntology.ai/paper/2407.20337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.20337"}},"official":{"repos":["aimagelab/code"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bivlc-extending-vision-language","slug":"bivlc-extending-vision-language","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","date":"2024-06-14","arxiv_id":"2406.09952","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/bivlc-extending-vision-language#ran","syntology_url":"https://syntology.ai/paper/2406.09952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09952"}},"official":{"repos":["imirandam/bivlc"],"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"]}}},{"url":"/paper/libra-building-decoupled-vision-system-on","slug":"libra-building-decoupled-vision-system-on","title":"Libra: Building Decoupled Vision System on Large Language Models","date":"2024-05-16","arxiv_id":"2405.10140","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/libra-building-decoupled-vision-system-on#ran","syntology_url":"https://syntology.ai/paper/2405.10140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10140"}},"official":{"repos":["yifanxu74/libra"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/comat-aligning-text-to-image-diffusion-model","slug":"comat-aligning-text-to-image-diffusion-model","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","date":"2024-04-04","arxiv_id":"2404.03653","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/comat-aligning-text-to-image-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2404.03653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03653"}},"official":{"repos":["caraj7/comat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/from-pixels-to-graphs-open-vocabulary-scene","slug":"from-pixels-to-graphs-open-vocabulary-scene","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","date":"2024-04-01","arxiv_id":"2404.00906","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-pixels-to-graphs-open-vocabulary-scene#ran","syntology_url":"https://syntology.ai/paper/2404.00906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00906"}},"official":{"repos":["shtuplus/pix2grp_cvpr2024"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-large-multimodal-models-against","slug":"benchmarking-large-multimodal-models-against","title":"Benchmarking Large Multimodal Models against Common Corruptions","date":"2024-01-22","arxiv_id":"2401.11943","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_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","sample_list":"/paper/benchmarking-large-multimodal-models-against#ran","syntology_url":"https://syntology.ai/paper/2401.11943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11943"}},"official":{"repos":["sail-sg/mmcbench"],"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"]}}},{"url":"/paper/pragmatic-radiology-report-generation","slug":"pragmatic-radiology-report-generation","title":"Pragmatic Radiology Report Generation","date":"2023-11-28","arxiv_id":"2311.17154","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pragmatic-radiology-report-generation#ran","syntology_url":"https://syntology.ai/paper/2311.17154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17154"}},"official":{"repos":["chicagohai/llm_radiology"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/removing-nsfw-concepts-from-vision-and","slug":"removing-nsfw-concepts-from-vision-and","title":"Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models","date":"2023-11-27","arxiv_id":"2311.16254","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/removing-nsfw-concepts-from-vision-and#ran","syntology_url":"https://syntology.ai/paper/2311.16254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16254"}},"official":{"repos":["aimagelab/safe-clip"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-grained-late-interaction-multi-modal-1","slug":"fine-grained-late-interaction-multi-modal-1","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","date":"2023-09-29","arxiv_id":"2309.17133","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-grained-late-interaction-multi-modal-1#ran","syntology_url":"https://syntology.ai/paper/2309.17133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.17133"}},"official":{"repos":["linweizhedragon/retrieval-augmented-visual-question-answering"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-one-to-one-rethinking-the-referring","slug":"beyond-one-to-one-rethinking-the-referring","title":"Beyond One-to-One: Rethinking the Referring Image Segmentation","date":"2023-08-26","arxiv_id":"2308.13853","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/beyond-one-to-one-rethinking-the-referring#ran","syntology_url":"https://syntology.ai/paper/2308.13853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.13853"}},"official":{"repos":["toggle1995/ris-dmmi"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/large-multilingual-models-pivot-zero-shot","slug":"large-multilingual-models-pivot-zero-shot","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","date":"2023-08-23","arxiv_id":"2308.12038","repositories_listed":2,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-multilingual-models-pivot-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2308.12038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12038"}},"official":{"repos":["openbmb/viscpm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multimodal-dataset-distillation-for-image","slug":"multimodal-dataset-distillation-for-image","title":"Vision-Language Dataset Distillation","date":"2023-08-15","arxiv_id":"2308.07545","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multimodal-dataset-distillation-for-image#ran","syntology_url":"https://syntology.ai/paper/2308.07545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.07545"}},"official":{"repos":["princetonvisualai/multimodal_dataset_distillation"],"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"]}}},{"url":"/paper/transferable-decoding-with-visual-entities","slug":"transferable-decoding-with-visual-entities","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","date":"2023-07-31","arxiv_id":"2307.16525","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":3,"n_ran_checked":5,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/transferable-decoding-with-visual-entities#ran","syntology_url":"https://syntology.ai/paper/2307.16525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.16525"}},"official":{"repos":["feielysia/viecap"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prior-prototype-representation-joint-learning","slug":"prior-prototype-representation-joint-learning","title":"PRIOR: Prototype Representation Joint Learning from Medical Images and Reports","date":"2023-07-24","arxiv_id":"2307.12577","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_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) · 1 unverified","sample_list":"/paper/prior-prototype-representation-joint-learning#ran","syntology_url":"https://syntology.ai/paper/2307.12577","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.12577"}},"official":{"repos":["qtacierp/prior"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bootstrapping-vision-language-learning-with-1","slug":"bootstrapping-vision-language-learning-with-1","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","date":"2023-07-13","arxiv_id":"2307.07063","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bootstrapping-vision-language-learning-with-1#ran","syntology_url":"https://syntology.ai/paper/2307.07063","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07063"}},"official":{"repos":["yiren-jian/blitext"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/magvlt-masked-generative-vision-and-language","slug":"magvlt-masked-generative-vision-and-language","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","date":"2023-03-21","arxiv_id":"2303.12208","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":5,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/magvlt-masked-generative-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2303.12208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12208"}},"official":{"repos":["kakaobrain/magvlt"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":5,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/one-transformer-fits-all-distributions-in","slug":"one-transformer-fits-all-distributions-in","title":"One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale","date":"2023-03-12","arxiv_id":"2303.06555","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/one-transformer-fits-all-distributions-in#ran","syntology_url":"https://syntology.ai/paper/2303.06555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06555"}},"official":{"repos":["thu-ml/unidiffuser"],"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":["official","unlocated"]}}},{"url":"/paper/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pix2struct-screenshot-parsing-as-pretraining","slug":"pix2struct-screenshot-parsing-as-pretraining","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","date":"2022-10-07","arxiv_id":"2210.03347","repositories_listed":4,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pix2struct-screenshot-parsing-as-pretraining#ran","syntology_url":"https://syntology.ai/paper/2210.03347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03347"}},"official":{"repos":["google-research/pix2struct"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/linearly-mapping-from-image-to-text-space","slug":"linearly-mapping-from-image-to-text-space","title":"Linearly Mapping from Image to Text Space","date":"2022-09-30","arxiv_id":"2209.15162","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linearly-mapping-from-image-to-text-space#ran","syntology_url":"https://syntology.ai/paper/2209.15162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15162"}},"official":{"repos":["jmerullo/limber"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/prefix-language-models-are-unified-modal","slug":"prefix-language-models-are-unified-modal","title":"Write and Paint: Generative Vision-Language Models are Unified Modal Learners","date":"2022-06-15","arxiv_id":"2206.07699","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/prefix-language-models-are-unified-modal#ran","syntology_url":"https://syntology.ai/paper/2206.07699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.07699"}},"official":{"repos":["shizhediao/davinci"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-the-openness-of-clip","slug":"rethinking-the-openness-of-clip","title":"Delving into the Openness of CLIP","date":"2022-06-04","arxiv_id":"2206.01986","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-the-openness-of-clip#ran","syntology_url":"https://syntology.ai/paper/2206.01986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.01986"}},"official":{"repos":["lancopku/clip-openness"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/git-a-generative-image-to-text-transformer","slug":"git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","date":"2022-05-27","arxiv_id":"2205.14100","repositories_listed":1,"syntology":{"n":21,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/git-a-generative-image-to-text-transformer#ran","syntology_url":"https://syntology.ai/paper/2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}},"official":{"repos":["microsoft/GenerativeImage2Text"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/translation-equivariant-image-quantizer-for","slug":"translation-equivariant-image-quantizer-for","title":"Exploration into Translation-Equivariant Image Quantization","date":"2021-12-01","arxiv_id":"2112.00384","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":10,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/translation-equivariant-image-quantizer-for#ran","syntology_url":"https://syntology.ai/paper/2112.00384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.00384"}},"official":{"repos":["wcshin-git/te-vqgan"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/zero-shot-image-to-text-generation-for-visual","slug":"zero-shot-image-to-text-generation-for-visual","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","date":"2021-11-29","arxiv_id":"2111.14447","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-image-to-text-generation-for-visual#ran","syntology_url":"https://syntology.ai/paper/2111.14447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.14447"}},"official":{"repos":["yoadtew/zero-shot-image-to-text"],"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":["official"]}}},{"url":"/paper/unifying-multimodal-transformer-for-bi","slug":"unifying-multimodal-transformer-for-bi","title":"Unifying Multimodal Transformer for Bi-directional Image and Text Generation","date":"2021-10-19","arxiv_id":"2110.09753","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unifying-multimodal-transformer-for-bi#ran","syntology_url":"https://syntology.ai/paper/2110.09753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09753"}},"official":{"repos":["researchmm/generate-it"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-factual-completeness-and","slug":"improving-factual-completeness-and","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","date":"2020-10-20","arxiv_id":"2010.10042","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-factual-completeness-and#ran","syntology_url":"https://syntology.ai/paper/2010.10042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10042"}},"official":{"repos":["ysmiura/ifcc"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}],"record_sha256":"71a16e981cffe734493b63bffdc6d7bf6a1da7a535f0f76035f2b5e06f9f6fa1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}