{"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":"/dataset/visual-question-answering-v2-0","name":"Visual Question Answering v2.0","full_name":"VQA v2.0","description_markdown":"Visual Question Answering (VQA) v2.0 is a dataset containing open-ended questions about images. These questions require an understanding of vision, language and commonsense knowledge to answer. It is the second version of the VQA dataset.\r\n\r\n- 265,016 images (COCO and abstract scenes)\r\n- At least 3 questions (5.4 questions on average) per image\r\n- 10 ground truth answers per question\r\n- 3 plausible (but likely incorrect) answers per question\r\n- Automatic evaluation metric\r\n\r\nThe [first version of the dataset](/dataset/visual-question-answering) was released in October 2015.","description_withheld":null,"homepage":"https://visualqa.org/","introduced_date":"2016-12-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/making-the-v-in-vqa-matter-elevating-the-role","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","first_author":"Yash Goyal","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Question Answering (VQA)","url":"/task/visual-question-answering","datasets_with_task":"/datasets/task/visual-question-answering"},{"name":"Visual Question Answering","url":"/task/visual-question-answering-1","datasets_with_task":"/datasets/task/visual-question-answering-1"}],"languages":[],"variants":["VQA 2.0","VQA v2","VQA v2 test-dev","VQA v2 test-std","Visual Question Answering v2.0","VQA v2 val"],"data_loaders":[{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#vqav2","frameworks":["pytorch"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/vision/dataset_readers/vqav2/","frameworks":["pytorch"]}],"num_papers_in_archive":366,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset_variant":"VQA v2 test-dev","rows":56,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"PaLI","paper":"/paper/pali-a-jointly-scaled-multilingual-language","metrics":{"Accuracy":"84.3"},"code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset_variant":"VQA v2 test-std","rows":38,"metrics":["overall","yes/no","number","other"],"first_row_in_archive_order":{"model":"BEiT-3","paper":"/paper/image-as-a-foreign-language-beit-pretraining","metrics":{"overall":"84.03"},"code_links":[{"title":"microsoft/unilm","url":"https://github.com/microsoft/unilm/tree/master/beit"},{"title":"lyan62/data-curation","url":"https://github.com/lyan62/data-curation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev-1","task":"Visual Question Answering","dataset_variant":"VQA v2 test-dev","rows":11,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"Accuracy":"82.30"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val","task":"Visual Question Answering (VQA)","dataset_variant":"VQA v2 val","rows":11,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G FlanT5 XXL (zero-shot)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"Accuracy":"65.2"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-val-1","task":"Visual Question Answering","dataset_variant":"VQA v2 val","rows":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"BLIP-2 ViT-G OPT 6.7B (fine-tuned)","paper":"/paper/blip-2-bootstrapping-language-image-pre","metrics":{"Accuracy":"82.19"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"salesforce/lavis","url":"https://github.com/salesforce/lavis"},{"title":"thudm/visualglm-6b","url":"https://github.com/thudm/visualglm-6b"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"junshutang/Make-It-3D","url":"https://github.com/junshutang/Make-It-3D"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"unispac/visual-adversarial-examples-jailbreak-large-language-models","url":"https://github.com/unispac/visual-adversarial-examples-jailbreak-large-language-models"},{"title":"yukw777/videoblip","url":"https://github.com/yukw777/videoblip"},{"title":"alibaba/graphtranslator","url":"https://github.com/alibaba/graphtranslator"},{"title":"gregor-ge/mblip","url":"https://github.com/gregor-ge/mblip"},{"title":"linzhiqiu/clip-flant5","url":"https://github.com/linzhiqiu/clip-flant5"},{"title":"kdr/videorag-mrr2024","url":"https://github.com/kdr/videorag-mrr2024"},{"title":"rabiulcste/vqazero","url":"https://github.com/rabiulcste/vqazero"},{"title":"jiwanchung/vlis","url":"https://github.com/jiwanchung/vlis"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-2/blip_2"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/blip_2"},{"title":"albertotestoni/ndq_visual_objects","url":"https://github.com/albertotestoni/ndq_visual_objects"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std-1","task":"Visual Question Answering","dataset_variant":"VQA v2 test-std","rows":3,"metrics":["Accuracy","number","other","overall","yes/no"],"first_row_in_archive_order":{"model":"LXMERT (low-magnitude pruning)","paper":"/paper/lxmert-model-compression-for-visual-question","metrics":{"Accuracy":"70.87"},"code_links":[{"title":"ghazaleh-mahmoodi/lxmert_compression","url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/lxmert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-1","task":"Visual Question Answering","dataset_variant":"VQA v2","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"RLHF-V","paper":"/paper/rlhf-v-towards-trustworthy-mllms-via-behavior","metrics":{"Accuracy":"80"},"code_links":[{"title":"openbmb/minicpm-v","url":"https://github.com/openbmb/minicpm-v"},{"title":"rlhf-v/rlhf-v","url":"https://github.com/rlhf-v/rlhf-v"},{"title":"tidedra/vl-rlhf","url":"https://github.com/tidedra/vl-rlhf"},{"title":"exgc/r1v-free","url":"https://github.com/exgc/r1v-free"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":66,"of":66,"counts":{"papers_with_a_benchmark_row":66,"with_a_code_link":59,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":66,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":29,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":29,"listed_every_run_a_failure_of_syntologys_instrument":4,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}}}},{"paper":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rlhf-v-towards-trustworthy-mllms-via-behavior","slug":"rlhf-v-towards-trustworthy-mllms-via-behavior","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","date":"2023-12-01","arxiv_id":"2312.00849","rows_on_this_dataset":1,"code_links":4,"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}}}},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prismer-a-vision-language-model-with-an","slug":"prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","arxiv_id":"2303.02506","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"paper":"/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","rows_on_this_dataset":18,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/toward-building-general-foundation-models-for","slug":"toward-building-general-foundation-models-for","title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","date":"2023-01-12","arxiv_id":"2301.05065","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}}}},{"paper":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","slug":"plug-and-play-vqa-zero-shot-vqa-by-conjoining","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","date":"2022-10-17","arxiv_id":"2210.08773","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining#ran","syntology_url":"https://syntology.ai/paper/2210.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08773"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/prompt-tuning-for-generative-multimodal","slug":"prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["ofa-sys/ofa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-tuning-for-generative-multimodal#ran","syntology_url":"https://syntology.ai/paper/2208.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02532"}}}},{"paper":"/paper/lako-knowledge-driven-visual-question","slug":"lako-knowledge-driven-visual-question","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","date":"2022-07-26","arxiv_id":"2207.12888","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hackerchenzhuo/LaKo"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lako-knowledge-driven-visual-question#ran","syntology_url":"https://syntology.ai/paper/2207.12888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12888"}}}},{"paper":"/paper/language-models-are-general-purpose","slug":"language-models-are-general-purpose","title":"Language Models are General-Purpose Interfaces","date":"2022-06-13","arxiv_id":"2206.06336","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":18,"samples_constructed":6,"samples_ran_checked":11,"samples_ran_instrument_failed":7,"samples_unverified":6,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}}}},{"paper":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ofa-sys/ofa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}}}},{"paper":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/achieving-human-parity-on-visual-question","slug":"achieving-human-parity-on-visual-question","title":"Achieving Human Parity on Visual Question Answering","date":"2021-11-17","arxiv_id":"2111.08896","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enabling-multimodal-generation-on-clip-via","slug":"enabling-multimodal-generation-on-clip-via","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["zengyan-97/x-vlm"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}}}},{"paper":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}}}},{"paper":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":22,"samples_constructed":8,"samples_ran_checked":16,"samples_ran_instrument_failed":6,"samples_unverified":15,"pointer_only_for_licence":32,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}}}},{"paper":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}}}},{"paper":"/paper/multimodal-few-shot-learning-with-frozen","slug":"multimodal-few-shot-learning-with-frozen","title":"Multimodal Few-Shot Learning with Frozen Language Models","date":"2021-06-25","arxiv_id":"2106.13884","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}}}},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["pzzhang/VinVL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/ernie-vil-knowledge-enhanced-vision-language","slug":"ernie-vil-knowledge-enhanced-vision-language","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","date":"2020-06-30","arxiv_id":"2006.16934","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":9,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}}}},{"paper":"/paper/deep-multimodal-neural-architecture-search","slug":"deep-multimodal-neural-architecture-search","title":"Deep Multimodal Neural Architecture Search","date":"2020-04-25","arxiv_id":"2004.12070","rows_on_this_dataset":1,"code_links":1,"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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":13,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}}}},{"paper":"/paper/visual-commonsense-r-cnn","slug":"visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","date":"2020-02-27","arxiv_id":"2002.12204","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Wangt-CN/VC-R-CNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-commonsense-r-cnn#ran","syntology_url":"https://syntology.ai/paper/2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}}}},{"paper":"/paper/in-defense-of-grid-features-for-visual","slug":"in-defense-of-grid-features-for-visual","title":"In Defense of Grid Features for Visual Question Answering","date":"2020-01-10","arxiv_id":"2001.03615","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/compact-trilinear-interaction-for-visual","slug":"compact-trilinear-interaction-for-visual","title":"Compact Trilinear Interaction for Visual Question Answering","date":"2019-09-26","arxiv_id":"1909.11874","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["aioz-ai/ICCV19_VQA-CTI"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/compact-trilinear-interaction-for-visual#ran","syntology_url":"https://syntology.ai/paper/1909.11874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11874"}}}},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jackroos/VL-BERT"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}}}},{"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","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}}}},{"paper":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":24,"pointer_only_for_licence":34,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}}}},{"paper":"/paper/graph-reasoning-networks-for-visual-question","slug":"graph-reasoning-networks-for-visual-question","title":"Bilinear Graph Networks for Visual Question Answering","date":"2019-07-23","arxiv_id":"1907.09815","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-modular-co-attention-networks-for-visual-1","slug":"deep-modular-co-attention-networks-for-visual-1","title":"Deep Modular Co-Attention Networks for Visual Question Answering","date":"2019-06-25","arxiv_id":"1906.10770","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["MILVLG/mcan-vqa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-modular-co-attention-networks-for-visual-1#ran","syntology_url":"https://syntology.ai/paper/1906.10770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10770"}}}},{"paper":"/paper/rubi-reducing-unimodal-biases-in-visual","slug":"rubi-reducing-unimodal-biases-in-visual","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","date":"2019-06-24","arxiv_id":"1906.10169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190600513","slug":"190600513","title":"Generating Question Relevant Captions to Aid Visual Question Answering","date":"2019-06-03","arxiv_id":"1906.00513","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-vqa-models-that-can-read","slug":"towards-vqa-models-that-can-read","title":"Towards VQA Models That Can Read","date":"2019-04-18","arxiv_id":"1904.08920","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/murel-multimodal-relational-reasoning-for","slug":"murel-multimodal-relational-reasoning-for","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","date":"2019-02-25","arxiv_id":"1902.09487","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/block-bilinear-superdiagonal-fusion-for","slug":"block-bilinear-superdiagonal-fusion-for","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","date":"2019-01-31","arxiv_id":"1902.00038","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Cadene/block.bootstrap.pytorch"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/block-bilinear-superdiagonal-fusion-for#ran","syntology_url":"https://syntology.ai/paper/1902.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00038"}}}},{"paper":"/paper/bilinear-attention-networks","slug":"bilinear-attention-networks","title":"Bilinear Attention Networks","date":"2018-05-21","arxiv_id":"1805.07932","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["jnhwkim/ban-vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bilinear-attention-networks#ran","syntology_url":"https://syntology.ai/paper/1805.07932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07932"}}}},{"paper":"/paper/learning-to-count-objects-in-natural-images","slug":"learning-to-count-objects-in-natural-images","title":"Learning to Count Objects in Natural Images for Visual Question Answering","date":"2018-02-15","arxiv_id":"1802.05766","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tips-and-tricks-for-visual-question-answering","slug":"tips-and-tricks-for-visual-question-answering","title":"Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge","date":"2017-08-09","arxiv_id":"1708.02711","rows_on_this_dataset":2,"code_links":10,"syntology":null},{"paper":"/paper/bottom-up-and-top-down-attention-for-image","slug":"bottom-up-and-top-down-attention-for-image","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","date":"2017-07-25","arxiv_id":"1707.07998","rows_on_this_dataset":1,"code_links":65,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["peteanderson80/bottom-up-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-and-top-down-attention-for-image#ran","syntology_url":"https://syntology.ai/paper/1707.07998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.07998"}}}},{"paper":"/paper/mutan-multimodal-tucker-fusion-for-visual","slug":"mutan-multimodal-tucker-fusion-for-visual","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","date":"2017-05-18","arxiv_id":"1705.06676","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/learning-to-reason-end-to-end-module-networks","slug":"learning-to-reason-end-to-end-module-networks","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","date":"2017-04-18","arxiv_id":"1704.05526","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/making-the-v-in-vqa-matter-elevating-the-role","slug":"making-the-v-in-vqa-matter-elevating-the-role","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","date":"2016-12-02","arxiv_id":"1612.00837","rows_on_this_dataset":3,"code_links":7,"syntology":null},{"paper":"/paper/multimodal-compact-bilinear-pooling-for","slug":"multimodal-compact-bilinear-pooling-for","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","date":"2016-06-06","arxiv_id":"1606.01847","rows_on_this_dataset":1,"code_links":10,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":9,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}}}},{"paper":"/paper/learning-to-localize-objects-improves-spatial","slug":"learning-to-localize-objects-improves-spatial","title":"Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs","date":"2024-04-11","arxiv_id":"2404.07449","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}}}},{"paper":"/paper/lyrics-boosting-fine-grained-language-vision","slug":"lyrics-boosting-fine-grained-language-vision","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","date":"2023-12-08","arxiv_id":"2312.05278","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rlhf-v-towards-trustworthy-mllms-via-behavior","slug":"rlhf-v-towards-trustworthy-mllms-via-behavior","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","date":"2023-12-01","arxiv_id":"2312.00849","rows_on_this_dataset":1,"code_links":4,"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","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/implicit-differentiable-outlier-detection","slug":"implicit-differentiable-outlier-detection","title":"Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-09-21","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}}}},{"paper":"/paper/one-peace-exploring-one-general","slug":"one-peace-exploring-one-general","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","date":"2023-05-18","arxiv_id":"2305.11172","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":2,"samples_ran_checked":4,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["OFA-Sys/ONE-PEACE"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/one-peace-exploring-one-general#ran","syntology_url":"https://syntology.ai/paper/2305.11172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.11172"}}}},{"paper":"/paper/valor-vision-audio-language-omni-perception","slug":"valor-vision-audio-language-omni-perception","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","date":"2023-04-17","arxiv_id":"2304.08345","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/prismer-a-vision-language-model-with-an","slug":"prismer-a-vision-language-model-with-an","title":"Prismer: A Vision-Language Model with Multi-Task Experts","date":"2023-03-04","arxiv_id":"2303.02506","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/differentiable-outlier-detection-enable","slug":"differentiable-outlier-detection-enable","title":"Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis","date":"2023-02-11","arxiv_id":"2302.05608","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-2-a-modularized-multi-modal-foundation","slug":"mplug-2-a-modularized-multi-modal-foundation","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","date":"2023-02-01","arxiv_id":"2302.00402","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":19,"samples_ran":17,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":9,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["alibaba/AliceMind"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mplug-2-a-modularized-multi-modal-foundation#ran","syntology_url":"https://syntology.ai/paper/2302.00402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00402"}}}},{"paper":"/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","rows_on_this_dataset":18,"code_links":17,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":4,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","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"}}}},{"paper":"/paper/toward-building-general-foundation-models-for","slug":"toward-building-general-foundation-models-for","title":"Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks","date":"2023-01-12","arxiv_id":"2301.05065","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/x-2-vlm-all-in-one-pre-trained-model-for","slug":"x-2-vlm-all-in-one-pre-trained-model-for","title":"X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks","date":"2022-11-22","arxiv_id":"2211.12402","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":3,"pointer_only_for_licence":6,"official":{"repos":["zengyan-97/x2-vlm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/x-2-vlm-all-in-one-pre-trained-model-for#ran","syntology_url":"https://syntology.ai/paper/2211.12402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12402"}}}},{"paper":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining","slug":"plug-and-play-vqa-zero-shot-vqa-by-conjoining","title":"Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training","date":"2022-10-17","arxiv_id":"2210.08773","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":2,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/plug-and-play-vqa-zero-shot-vqa-by-conjoining#ran","syntology_url":"https://syntology.ai/paper/2210.08773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.08773"}}}},{"paper":"/paper/pali-a-jointly-scaled-multilingual-language","slug":"pali-a-jointly-scaled-multilingual-language","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","date":"2022-09-14","arxiv_id":"2209.06794","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["google-research/big_vision"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/pali-a-jointly-scaled-multilingual-language#ran","syntology_url":"https://syntology.ai/paper/2209.06794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.06794"}}}},{"paper":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/prompt-tuning-for-generative-multimodal","slug":"prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["ofa-sys/ofa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/prompt-tuning-for-generative-multimodal#ran","syntology_url":"https://syntology.ai/paper/2208.02532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.02532"}}}},{"paper":"/paper/lako-knowledge-driven-visual-question","slug":"lako-knowledge-driven-visual-question","title":"LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection","date":"2022-07-26","arxiv_id":"2207.12888","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["hackerchenzhuo/LaKo"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lako-knowledge-driven-visual-question#ran","syntology_url":"https://syntology.ai/paper/2207.12888","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12888"}}}},{"paper":"/paper/language-models-are-general-purpose","slug":"language-models-are-general-purpose","title":"Language Models are General-Purpose Interfaces","date":"2022-06-13","arxiv_id":"2206.06336","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/mplug-effective-and-efficient-vision-language","slug":"mplug-effective-and-efficient-vision-language","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","date":"2022-05-24","arxiv_id":"2205.12005","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/coca-contrastive-captioners-are-image-text","slug":"coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":17,"samples_ran":10,"samples_constructed":5,"samples_ran_checked":9,"samples_ran_instrument_failed":1,"samples_unverified":7,"pointer_only_for_licence":2,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coca-contrastive-captioners-are-image-text#ran","syntology_url":"https://syntology.ai/paper/2205.01917","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01917"}}}},{"paper":"/paper/flamingo-a-visual-language-model-for-few-shot-1","slug":"flamingo-a-visual-language-model-for-few-shot-1","title":"Flamingo: a Visual Language Model for Few-Shot Learning","date":"2022-04-29","arxiv_id":"2204.14198","rows_on_this_dataset":3,"code_links":5,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":24,"samples_ran":18,"samples_constructed":6,"samples_ran_checked":11,"samples_ran_instrument_failed":7,"samples_unverified":6,"pointer_only_for_licence":8,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/flamingo-a-visual-language-model-for-few-shot-1#ran","syntology_url":"https://syntology.ai/paper/2204.14198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.14198"}}}},{"paper":"/paper/unifying-architectures-tasks-and-modalities","slug":"unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["ofa-sys/ofa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unifying-architectures-tasks-and-modalities#ran","syntology_url":"https://syntology.ai/paper/2202.03052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.03052"}}}},{"paper":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/achieving-human-parity-on-visual-question","slug":"achieving-human-parity-on-visual-question","title":"Achieving Human Parity on Visual Question Answering","date":"2021-11-17","arxiv_id":"2111.08896","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/enabling-multimodal-generation-on-clip-via","slug":"enabling-multimodal-generation-on-clip-via","title":"Enabling Multimodal Generation on CLIP via Vision-Language Knowledge Distillation","date":"2021-11-16","arxiv_id":null,"rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/multi-grained-vision-language-pre-training","slug":"multi-grained-vision-language-pre-training","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","date":"2021-11-16","arxiv_id":"2111.08276","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["zengyan-97/x-vlm"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/multi-grained-vision-language-pre-training#ran","syntology_url":"https://syntology.ai/paper/2111.08276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.08276"}}}},{"paper":"/paper/vlmo-unified-vision-language-pre-training","slug":"vlmo-unified-vision-language-pre-training","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","date":"2021-11-03","arxiv_id":"2111.02358","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/a-good-prompt-is-worth-millions-of-parameters","slug":"a-good-prompt-is-worth-millions-of-parameters","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","date":"2021-10-16","arxiv_id":"2110.08484","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":2,"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}}}},{"paper":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":22,"samples_constructed":8,"samples_ran_checked":16,"samples_ran_instrument_failed":6,"samples_unverified":15,"pointer_only_for_licence":32,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}}}},{"paper":"/paper/align-before-fuse-vision-and-language","slug":"align-before-fuse-vision-and-language","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","date":"2021-07-16","arxiv_id":"2107.07651","rows_on_this_dataset":2,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":3,"samples_unverified":1,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/align-before-fuse-vision-and-language#ran","syntology_url":"https://syntology.ai/paper/2107.07651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.07651"}}}},{"paper":"/paper/multimodal-few-shot-learning-with-frozen","slug":"multimodal-few-shot-learning-with-frozen","title":"Multimodal Few-Shot Learning with Frozen Language Models","date":"2021-06-25","arxiv_id":"2106.13884","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/vilt-vision-and-language-transformer-without","slug":"vilt-vision-and-language-transformer-without","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","date":"2021-02-05","arxiv_id":"2102.03334","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":1,"samples_constructed":1,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":1,"official":{"repos":["dandelin/vilt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilt-vision-and-language-transformer-without#ran","syntology_url":"https://syntology.ai/paper/2102.03334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.03334"}}}},{"paper":"/paper/vinvl-making-visual-representations-matter-in","slug":"vinvl-making-visual-representations-matter-in","title":"VinVL: Revisiting Visual Representations in Vision-Language Models","date":"2021-01-02","arxiv_id":"2101.00529","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["pzzhang/VinVL"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vinvl-making-visual-representations-matter-in#ran","syntology_url":"https://syntology.ai/paper/2101.00529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00529"}}}},{"paper":"/paper/ernie-vil-knowledge-enhanced-vision-language","slug":"ernie-vil-knowledge-enhanced-vision-language","title":"ERNIE-ViL: Knowledge Enhanced Vision-Language Representations Through Scene Graph","date":"2020-06-30","arxiv_id":"2006.16934","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":12,"samples_constructed":9,"samples_ran_checked":9,"samples_ran_instrument_failed":3,"samples_unverified":3,"pointer_only_for_licence":2,"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}}}},{"paper":"/paper/deep-multimodal-neural-architecture-search","slug":"deep-multimodal-neural-architecture-search","title":"Deep Multimodal Neural Architecture Search","date":"2020-04-25","arxiv_id":"2004.12070","rows_on_this_dataset":1,"code_links":1,"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","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":23,"samples_ran":13,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":3,"samples_unverified":10,"pointer_only_for_licence":1,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/oscar-object-semantics-aligned-pre-training#ran","syntology_url":"https://syntology.ai/paper/2004.06165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.06165"}}}},{"paper":"/paper/visual-commonsense-r-cnn","slug":"visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","date":"2020-02-27","arxiv_id":"2002.12204","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["Wangt-CN/VC-R-CNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visual-commonsense-r-cnn#ran","syntology_url":"https://syntology.ai/paper/2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}}}},{"paper":"/paper/in-defense-of-grid-features-for-visual","slug":"in-defense-of-grid-features-for-visual","title":"In Defense of Grid Features for Visual Question Answering","date":"2020-01-10","arxiv_id":"2001.03615","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/compact-trilinear-interaction-for-visual","slug":"compact-trilinear-interaction-for-visual","title":"Compact Trilinear Interaction for Visual Question Answering","date":"2019-09-26","arxiv_id":"1909.11874","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["aioz-ai/ICCV19_VQA-CTI"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/compact-trilinear-interaction-for-visual#ran","syntology_url":"https://syntology.ai/paper/1909.11874","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11874"}}}},{"paper":"/paper/uniter-learning-universal-image-text-1","slug":"uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":3,"samples_unverified":0,"pointer_only_for_licence":2,"official":{"repos":["ChenRocks/UNITER"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/uniter-learning-universal-image-text-1#ran","syntology_url":"https://syntology.ai/paper/1909.11740","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11740"}}}},{"paper":"/paper/unified-vision-language-pre-training-for","slug":"unified-vision-language-pre-training-for","title":"Unified Vision-Language Pre-Training for Image Captioning and VQA","date":"2019-09-24","arxiv_id":"1909.11059","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":5,"samples_unverified":3,"pointer_only_for_licence":14,"official":{"repos":["LuoweiZhou/VLP"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/unified-vision-language-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/1909.11059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.11059"}}}},{"paper":"/paper/vl-bert-pre-training-of-generic-visual","slug":"vl-bert-pre-training-of-generic-visual","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","date":"2019-08-22","arxiv_id":"1908.08530","rows_on_this_dataset":3,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["jackroos/VL-BERT"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vl-bert-pre-training-of-generic-visual#ran","syntology_url":"https://syntology.ai/paper/1908.08530","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08530"}}}},{"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","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":4,"samples_constructed":4,"samples_ran_checked":4,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":3,"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/lxmert-learning-cross-modality-encoder#ran","syntology_url":"https://syntology.ai/paper/1908.07490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07490"}}}},{"paper":"/paper/visualbert-a-simple-and-performant-baseline","slug":"visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","arxiv_id":"1908.03557","rows_on_this_dataset":2,"code_links":10,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":4,"samples_constructed":2,"samples_ran_checked":2,"samples_ran_instrument_failed":2,"samples_unverified":5,"pointer_only_for_licence":6,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/visualbert-a-simple-and-performant-baseline#ran","syntology_url":"https://syntology.ai/paper/1908.03557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.03557"}}}},{"paper":"/paper/vilbert-pretraining-task-agnostic","slug":"vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","arxiv_id":"1908.02265","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":34,"samples_ran":10,"samples_constructed":6,"samples_ran_checked":8,"samples_ran_instrument_failed":2,"samples_unverified":24,"pointer_only_for_licence":34,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/vilbert-pretraining-task-agnostic#ran","syntology_url":"https://syntology.ai/paper/1908.02265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.02265"}}}},{"paper":"/paper/graph-reasoning-networks-for-visual-question","slug":"graph-reasoning-networks-for-visual-question","title":"Bilinear Graph Networks for Visual Question Answering","date":"2019-07-23","arxiv_id":"1907.09815","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/deep-modular-co-attention-networks-for-visual-1","slug":"deep-modular-co-attention-networks-for-visual-1","title":"Deep Modular Co-Attention Networks for Visual Question Answering","date":"2019-06-25","arxiv_id":"1906.10770","rows_on_this_dataset":2,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["MILVLG/mcan-vqa"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-modular-co-attention-networks-for-visual-1#ran","syntology_url":"https://syntology.ai/paper/1906.10770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10770"}}}},{"paper":"/paper/rubi-reducing-unimodal-biases-in-visual","slug":"rubi-reducing-unimodal-biases-in-visual","title":"RUBi: Reducing Unimodal Biases in Visual Question Answering","date":"2019-06-24","arxiv_id":"1906.10169","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/190600513","slug":"190600513","title":"Generating Question Relevant Captions to Aid Visual Question Answering","date":"2019-06-03","arxiv_id":"1906.00513","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/towards-vqa-models-that-can-read","slug":"towards-vqa-models-that-can-read","title":"Towards VQA Models That Can Read","date":"2019-04-18","arxiv_id":"1904.08920","rows_on_this_dataset":1,"code_links":7,"syntology":null},{"paper":"/paper/murel-multimodal-relational-reasoning-for","slug":"murel-multimodal-relational-reasoning-for","title":"MUREL: Multimodal Relational Reasoning for Visual Question Answering","date":"2019-02-25","arxiv_id":"1902.09487","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/block-bilinear-superdiagonal-fusion-for","slug":"block-bilinear-superdiagonal-fusion-for","title":"BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection","date":"2019-01-31","arxiv_id":"1902.00038","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":2,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["Cadene/block.bootstrap.pytorch"],"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"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/block-bilinear-superdiagonal-fusion-for#ran","syntology_url":"https://syntology.ai/paper/1902.00038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.00038"}}}},{"paper":"/paper/bilinear-attention-networks","slug":"bilinear-attention-networks","title":"Bilinear Attention Networks","date":"2018-05-21","arxiv_id":"1805.07932","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":13,"samples_constructed":0,"samples_ran_checked":13,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["jnhwkim/ban-vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bilinear-attention-networks#ran","syntology_url":"https://syntology.ai/paper/1805.07932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.07932"}}}},{"paper":"/paper/learning-to-count-objects-in-natural-images","slug":"learning-to-count-objects-in-natural-images","title":"Learning to Count Objects in Natural Images for Visual Question Answering","date":"2018-02-15","arxiv_id":"1802.05766","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/tips-and-tricks-for-visual-question-answering","slug":"tips-and-tricks-for-visual-question-answering","title":"Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challenge","date":"2017-08-09","arxiv_id":"1708.02711","rows_on_this_dataset":2,"code_links":10,"syntology":null},{"paper":"/paper/bottom-up-and-top-down-attention-for-image","slug":"bottom-up-and-top-down-attention-for-image","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","date":"2017-07-25","arxiv_id":"1707.07998","rows_on_this_dataset":1,"code_links":65,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":8,"samples_unverified":0,"pointer_only_for_licence":6,"official":{"repos":["peteanderson80/bottom-up-attention"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/bottom-up-and-top-down-attention-for-image#ran","syntology_url":"https://syntology.ai/paper/1707.07998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.07998"}}}},{"paper":"/paper/mutan-multimodal-tucker-fusion-for-visual","slug":"mutan-multimodal-tucker-fusion-for-visual","title":"MUTAN: Multimodal Tucker Fusion for Visual Question Answering","date":"2017-05-18","arxiv_id":"1705.06676","rows_on_this_dataset":2,"code_links":6,"syntology":null},{"paper":"/paper/learning-to-reason-end-to-end-module-networks","slug":"learning-to-reason-end-to-end-module-networks","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","date":"2017-04-18","arxiv_id":"1704.05526","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/making-the-v-in-vqa-matter-elevating-the-role","slug":"making-the-v-in-vqa-matter-elevating-the-role","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","date":"2016-12-02","arxiv_id":"1612.00837","rows_on_this_dataset":3,"code_links":7,"syntology":null},{"paper":"/paper/multimodal-compact-bilinear-pooling-for","slug":"multimodal-compact-bilinear-pooling-for","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","date":"2016-06-06","arxiv_id":"1606.01847","rows_on_this_dataset":1,"code_links":10,"syntology":null}],"papers_where_code_ran":33,"papers_where_code_ran_first_page":"/dataset/visual-question-answering-v2-0/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/visual-question-answering-v2-0/papers/ran/1","json":"/dataset/visual-question-answering-v2-0/papers/ran/1.json","rows":33}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":34,"samples_harvested":313,"samples_ran":203,"samples_constructed":56,"samples_ran_checked":132,"samples_ran_instrument_failed":71,"samples_unverified":110,"pointer_only_for_licence":140,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":33,"papers_with_a_run_with_no_instrument_failure":29,"papers_where_every_run_was_an_instrument_failure":4,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","since_archive":"/sota/visual-question-answering-on-vqa-v2-test-std#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std-1","since_archive":"/sota/visual-question-answering-on-vqa-v2-test-std-1#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"29ec2b177c1d702a5dfa401a10a0953663e7cc2fff4cf13866f5dcb0db06abfd","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}