{"url":"/task/generative-visual-question-answering","name":"Generative Visual Question Answering","slug":"generative-visual-question-answering","description_markdown":"Generating answers in free form to questions posed about images.","categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":9,"papers_with_code":7,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/generative-visual-question-answering-on-pmc","slug":"generative-visual-question-answering-on-pmc","dataset":"PMC-VQA","dataset_url":"/dataset/pmc-vqa","rows_in_archive":3,"metrics":["BLEU-1"],"first_row_in_archive_order":{"model":"MedVInT","paper_title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","paper_url":"/paper/pmc-vqa-visual-instruction-tuning-for-medical","paper_date":"2023-05-17","arxiv_id":"2305.10415","code_links":[{"title":"xiaoman-zhang/PMC-VQA","url":"https://github.com/xiaoman-zhang/PMC-VQA"},{"title":"zihanzhaosjtu/librisqa","url":"https://github.com/zihanzhaosjtu/librisqa"}],"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/pmc-vqa","name":"PMC-VQA","full_name":"","num_papers_in_archive":55}],"subtasks":[{"url":"/task/video-based-generative-performance","name":"Video-based Generative Performance Benchmarking"}],"parent_tasks":[{"url":"/task/visual-question-answering","name":"Visual Question Answering (VQA)"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":9,"items":[{"url":"/paper/blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/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","repositories_listed":5,"syntology":{"n":24,"n_ran":18,"n_unverified":6,"n_pointer_only":7}},{"url":"/paper/pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10415","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/vgat-a-cancer-survival-analysis-framework","title":"VGAT: A Cancer Survival Analysis Framework Transitioning from Generative Visual Question Answering to Genomic Reconstruction","date":"2025-03-25","arxiv_id":"2503.19367","repositories_listed":1,"syntology":null},{"url":"/paper/2408-00300","title":"Towards Flexible Evaluation for Generative Visual Question Answering","date":"2024-08-01","arxiv_id":"2408.00300","repositories_listed":1,"syntology":null},{"url":"/paper/wsi-vqa-interpreting-whole-slide-images-by","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","date":"2024-07-08","arxiv_id":"2407.05603","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/multimodal-prompt-retrieval-for-generative","title":"Multimodal Prompt Retrieval for Generative Visual Question Answering","date":"2023-06-30","arxiv_id":"2306.17675","repositories_listed":1,"syntology":null}],"syntology_records":4,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}