{"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/blip/papers/ran/1","list_of":"/method/blip","method":"BLIP","archive":{"snapshot":"2025-07-28"},"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 isolate this method inside it.","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":[1,16],"of":16,"counts":{"archive_papers_tagged":93,"with_a_code_link":44,"where_syntology_ran_a_sample":16,"not_listed_spam_title":0,"listed":93,"listed_where_code_ran":16,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":16,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":16,"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"},"first_page":"/method/blip/papers/ran/1","prev":null,"next":null,"papers":[{"paper":"/paper/multiclimate-multimodal-stance-detection-on","slug":"multiclimate-multimodal-stance-detection-on","title":"MultiClimate: Multimodal Stance Detection on Climate Change Videos","date":"2024-09-26","arxiv_id":"2409.18346","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"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","official":{"repos":["werywjw/multiclimate"],"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"]}}},{"paper":"/paper/prior-knowledge-integration-via-llm-encoding","slug":"prior-knowledge-integration-via-llm-encoding","title":"Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval","date":"2024-07-21","arxiv_id":"2407.15051","n_code_links":1,"syntology":{"ran":8,"of":11,"n_ran_checked":5,"n_instrument":3,"unverified":3,"pointer_only":9,"phrase":"8 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; 3 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fletcherjiang/llmepet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/madtp-multimodal-alignment-guided-dynamic","slug":"madtp-multimodal-alignment-guided-dynamic","title":"MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer","date":"2024-03-05","arxiv_id":"2403.02991","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":2,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["double125/madtp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/colorswap-a-color-and-word-order-dataset-for","slug":"colorswap-a-color-and-word-order-dataset-for","title":"ColorSwap: A Color and Word Order Dataset for Multimodal Evaluation","date":"2024-02-07","arxiv_id":"2402.04492","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["top34051/colorswap"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/grounded-sam-assembling-open-world-models-for","slug":"grounded-sam-assembling-open-world-models-for","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","date":"2024-01-25","arxiv_id":"2401.14159","n_code_links":5,"syntology":{"ran":15,"of":15,"n_ran_checked":10,"n_instrument":5,"unverified":0,"pointer_only":5,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["IDEA-Research/Grounded-Segment-Anything"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/scimmir-benchmarking-scientific-multi-modal","slug":"scimmir-benchmarking-scientific-multi-modal","title":"SciMMIR: Benchmarking Scientific Multi-modal Information Retrieval","date":"2024-01-24","arxiv_id":"2401.13478","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":10,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["wusiwei0410/scimmir"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/language-guided-visual-question-answering","slug":"language-guided-visual-question-answering","title":"Language Guided Visual Question Answering: Elevate Your Multimodal Language Model Using Knowledge-Enriched Prompts","date":"2023-10-31","arxiv_id":"2310.20159","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 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; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["declare-lab/lg-vqa"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-s-up-with-vision-language-models","slug":"what-s-up-with-vision-language-models","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","date":"2023-10-30","arxiv_id":"2310.19785","n_code_links":2,"syntology":{"ran":5,"of":9,"n_ran_checked":3,"n_instrument":2,"unverified":4,"pointer_only":8,"phrase":"5 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; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["amitakamath/whatsup_vlms"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/vision-by-language-for-training-free","slug":"vision-by-language-for-training-free","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","date":"2023-10-13","arxiv_id":"2310.09291","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":2,"phrase":"4 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; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["explainableml/vision_by_language"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/fire-food-image-to-recipe-generation","slug":"fire-food-image-to-recipe-generation","title":"FIRE: Food Image to REcipe generation","date":"2023-08-28","arxiv_id":"2308.14391","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":10,"n_instrument":2,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 2 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","official":{"repos":["prateekchhikara/fire"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/figcaps-hf-a-figure-to-caption-generative","slug":"figcaps-hf-a-figure-to-caption-generative","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","date":"2023-07-20","arxiv_id":"2307.10867","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":1,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"2 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["figcapshf/figcapshf"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/probvlm-probabilistic-adapter-for-frozen","slug":"probvlm-probabilistic-adapter-for-frozen","title":"ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models","date":"2023-07-01","arxiv_id":"2307.00398","n_code_links":1,"syntology":{"ran":8,"of":15,"n_ran_checked":5,"n_instrument":3,"unverified":7,"pointer_only":2,"phrase":"8 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; 3 where Syntology's instrument failed) · 7 unverified","official":{"repos":["explainableml/probvlm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-evaluating-adversarial-robustness-of-large","slug":"on-evaluating-adversarial-robustness-of-large","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","date":"2023-05-26","arxiv_id":"2305.16934","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yunqing-me/attackvlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/anything-3d-towards-single-view-anything","slug":"anything-3d-towards-single-view-anything","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","date":"2023-04-19","arxiv_id":"2304.10261","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["anything-of-anything/anything-3d"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cross-domain-image-captioning-with","slug":"cross-domain-image-captioning-with","title":"Cross-Domain Image Captioning with Discriminative Finetuning","date":"2023-04-04","arxiv_id":"2304.01662","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":["facebookresearch/EGG"],"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/position-guided-text-prompt-for-vision","slug":"position-guided-text-prompt-for-vision","title":"Position-guided Text Prompt for Vision-Language Pre-training","date":"2022-12-19","arxiv_id":"2212.09737","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":1,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sail-sg/ptp"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"30124fe7b879797166e05d2540b98a85e96c785bac53fe6ac191578b3e2f24ac","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}