{"url":"/task/multi-modal-dialogue-generation","name":"Multi-modal Dialogue Generation","slug":"multi-modal-dialogue-generation","description_markdown":"Image credit: [OpenViDial](https://github.com/ShannonAI/OpenViDial)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":3,"papers_with_code":3,"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":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multi-modal-dialogue-generation-on-openvidial","slug":"multi-modal-dialogue-generation-on-openvidial","dataset":"OpenViDial 2.0","dataset_url":"/dataset/openvidial-2-0","rows_in_archive":4,"metrics":["BLEU","Dis-1","Dis-2","Dis-3","Dis-4"],"first_row_in_archive_order":{"model":"FV (w/o MI)","paper_title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","paper_url":"/paper/openvidial-2-0-a-larger-scale-open-domain","paper_date":"2021-09-27","arxiv_id":"2109.12761","code_links":[{"title":"ShannonAI/OpenViDial","url":"https://github.com/ShannonAI/OpenViDial"}],"syntology":null}}],"datasets":[{"url":"/dataset/mmdialog","name":"MMDialog","full_name":"","num_papers_in_archive":17},{"url":"/dataset/mmchat","name":"MMChat","full_name":"","num_papers_in_archive":5},{"url":"/dataset/openvidial-2-0","name":"OpenViDial 2.0","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/dialogue-generation","name":"Dialogue Generation"}],"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":3,"of":3,"tagged_in_all":3,"items":[{"url":"/paper/an-end-to-end-model-for-photo-sharing-multi","title":"An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation","date":"2024-08-16","arxiv_id":"2408.08650","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-very-long-term-conversational","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","date":"2024-02-27","arxiv_id":"2402.17753","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":7}},{"url":"/paper/openvidial-2-0-a-larger-scale-open-domain","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","date":"2021-09-27","arxiv_id":"2109.12761","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}