{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/visual-dialogue","name":"Visual Dialog","slug":"visual-dialogue","description_markdown":"Visual Dialog requires an AI agent to hold a meaningful dialog with humans in natural, conversational language about visual content. Specifically, given an image, a dialog history, and a follow-up question about the image, the task is to answer the question.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":118,"papers_with_code":56,"benchmarks":8,"benchmark_tables_in_archive":8,"benchmark_tables_shown":8,"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":9,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-dialog-on-visual-dialog-v1-0-test-std","slug":"visual-dialog-on-visual-dialog-v1-0-test-std","dataset":"Visual Dialog v1.0 test-std","dataset_url":"/dataset/visdial","rows_in_archive":80,"metrics":["NDCG (x 100)","MRR (x 100)","R@1","R@5","R@10","Mean"],"first_row_in_archive_order":{"model":"Single","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-visdial-v09-val","slug":"visual-dialog-on-visdial-v09-val","dataset":"VisDial v0.9 val","dataset_url":"/dataset/visdial","rows_in_archive":18,"metrics":["MRR","R@1","R@10","R@5","Mean Rank"],"first_row_in_archive_order":{"model":"9xFGA (VGG)","paper_title":"Factor Graph Attention","paper_url":"/paper/factor-graph-attention","paper_date":"2019-04-11","arxiv_id":"1904.05880","code_links":[{"title":"idansc/fga","url":"https://github.com/idansc/fga"}],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-visdial-v10-test-std","slug":"visual-dialog-on-visdial-v10-test-std","dataset":"VisDial v1.0 test-std","dataset_url":"/dataset/visdial","rows_in_archive":3,"metrics":["MRR","Mean Rank","NDCG","R@1","R@10","R@5"],"first_row_in_archive_order":{"model":"5xFGA + LS*+","paper_title":"Ensemble of MRR and NDCG models for Visual Dialog","paper_url":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","paper_date":"2021-04-15","arxiv_id":"2104.07511","code_links":[{"title":"idansc/mrr-ndcg","url":"https://github.com/idansc/mrr-ndcg"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual#ran","syntology_url":"https://syntology.ai/paper/2104.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07511"}},"official":{"repos":["idansc/mrr-ndcg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/visual-dialog-on-blendedskilltalk","slug":"visual-dialog-on-blendedskilltalk","dataset":"BlendedSkillTalk","dataset_url":"/dataset/blended-skill-talk","rows_in_archive":1,"metrics":["BLEU-4","F1","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi-Modal BlenderBot","paper_title":"Multi-Modal Open-Domain Dialogue","paper_url":"/paper/multi-modal-open-domain-dialogue","paper_date":"2020-10-02","arxiv_id":"2010.01082","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-convai2","slug":"visual-dialog-on-convai2","dataset":"ConvAI2","dataset_url":"/dataset/convai2","rows_in_archive":1,"metrics":["BLEU-4","F1","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi-Modal BlenderBot","paper_title":"Multi-Modal Open-Domain Dialogue","paper_url":"/paper/multi-modal-open-domain-dialogue","paper_date":"2020-10-02","arxiv_id":"2010.01082","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-empatheticdialogues","slug":"visual-dialog-on-empatheticdialogues","dataset":"EmpatheticDialogues","dataset_url":"/dataset/empatheticdialogues","rows_in_archive":1,"metrics":["BLEU-4","F1","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi-Modal BlenderBot","paper_title":"Multi-Modal Open-Domain Dialogue","paper_url":"/paper/multi-modal-open-domain-dialogue","paper_date":"2020-10-02","arxiv_id":"2010.01082","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-image-chat","slug":"visual-dialog-on-image-chat","dataset":"Image-Chat","dataset_url":"/dataset/image-chat","rows_in_archive":1,"metrics":["BLEU-4","F1","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi-Modal BlenderBot","paper_title":"Multi-Modal Open-Domain Dialogue","paper_url":"/paper/multi-modal-open-domain-dialogue","paper_date":"2020-10-02","arxiv_id":"2010.01082","code_links":[],"syntology":null}},{"leaderboard":"/sota/visual-dialog-on-wizard-of-wikipedia","slug":"visual-dialog-on-wizard-of-wikipedia","dataset":"Wizard of Wikipedia","dataset_url":"/dataset/wizard-of-wikipedia","rows_in_archive":1,"metrics":["BLEU-4","F1","ROUGE-L"],"first_row_in_archive_order":{"model":"Multi-Modal BlenderBot","paper_title":"Multi-Modal Open-Domain Dialogue","paper_url":"/paper/multi-modal-open-domain-dialogue","paper_date":"2020-10-02","arxiv_id":"2010.01082","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/visdial","name":"VisDial","full_name":"Visual Dialog","num_papers_in_archive":159},{"url":"/dataset/wizard-of-wikipedia","name":"Wizard of Wikipedia","full_name":"","num_papers_in_archive":145},{"url":"/dataset/convai2","name":"ConvAI2","full_name":"Conversational Intelligence Challenge 2","num_papers_in_archive":100},{"url":"/dataset/empatheticdialogues","name":"EmpatheticDialogues","full_name":"","num_papers_in_archive":64},{"url":"/dataset/blended-skill-talk","name":"Blended Skill Talk","full_name":"Blended Skill Talk","num_papers_in_archive":32},{"url":"/dataset/image-chat","name":"Image-Chat","full_name":"","num_papers_in_archive":31},{"url":"/dataset/photobook","name":"PhotoBook","full_name":"","num_papers_in_archive":11},{"url":"/dataset/clevr-dialog","name":"CLEVR-Dialog","full_name":"CLEVR-Dialog","num_papers_in_archive":10},{"url":"/dataset/vispro","name":"VisPro","full_name":"VisPro","num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[{"url":"/task/dialogue","name":"Dialogue"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":118,"of_with_code":56,"tagged_in_all":118,"counts":{"archive_papers_tagged":118,"with_a_code_link":56,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":118,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/visual-dialog","slug":"visual-dialog","title":"Visual Dialog","date":"2016-11-26","arxiv_id":"1611.08669","repositories_listed":11,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-dialog#ran","syntology_url":"https://syntology.ai/paper/1611.08669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08669"}},"official":{"repos":["batra-mlp-lab/visdial-amt-chat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/hierarchical-question-image-co-attention-for","slug":"hierarchical-question-image-co-attention-for","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","date":"2016-05-31","arxiv_id":"1606.00061","repositories_listed":9,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/hierarchical-question-image-co-attention-for#ran","syntology_url":"https://syntology.ai/paper/1606.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00061"}},"official":{"repos":["jiasenlu/HieCoAttenVQA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/learning-cooperative-visual-dialog-agents","slug":"learning-cooperative-visual-dialog-agents","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","date":"2017-03-20","arxiv_id":"1703.06585","repositories_listed":7,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-cooperative-visual-dialog-agents#ran","syntology_url":"https://syntology.ai/paper/1703.06585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.06585"}},"official":null}},{"url":"/paper/audio-visual-scene-aware-dialog-avsd","slug":"audio-visual-scene-aware-dialog-avsd","title":"Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7","date":"2018-06-01","arxiv_id":"1806.00525","repositories_listed":4,"syntology":null},{"url":"/paper/perceptual-score-what-data-modalities-does","slug":"perceptual-score-what-data-modalities-does","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","date":"2021-10-27","arxiv_id":"2110.14375","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/perceptual-score-what-data-modalities-does#ran","syntology_url":"https://syntology.ai/paper/2110.14375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14375"}},"official":{"repos":["itaigat/perceptual-score"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":2,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mini-gemini-mining-the-potential-of-multi#ran","syntology_url":"https://syntology.ai/paper/2403.18814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18814"}},"official":{"repos":["dvlab-research/minigemini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-dialog-must-go-on-improving-visual-dialog","slug":"the-dialog-must-go-on-improving-visual-dialog","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","date":"2022-05-25","arxiv_id":"2205.12502","repositories_listed":2,"syntology":null},{"url":"/paper/where-are-you-localization-from-embodied","slug":"where-are-you-localization-from-embodied","title":"Where Are You? Localization from Embodied Dialog","date":"2020-11-16","arxiv_id":"2011.08277","repositories_listed":2,"syntology":null},{"url":"/paper/history-for-visual-dialog-do-we-really-need","slug":"history-for-visual-dialog-do-we-really-need","title":"History for Visual Dialog: Do we really need it?","date":"2020-05-08","arxiv_id":"2005.07493","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-pretraining-for-visual-dialog-a","slug":"large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","arxiv_id":"1912.02379","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-pretraining-for-visual-dialog-a#ran","syntology_url":"https://syntology.ai/paper/1912.02379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02379"}},"official":{"repos":["vmurahari3/visdial-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dual-attention-networks-for-visual-reference","slug":"dual-attention-networks-for-visual-reference","title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","date":"2019-02-25","arxiv_id":"1902.09368","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dual-attention-networks-for-visual-reference#ran","syntology_url":"https://syntology.ai/paper/1902.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09368"}},"official":{"repos":["gicheonkang/DAN-VisDial"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/visual-dialogue-without-vision-or-dialogue","slug":"visual-dialogue-without-vision-or-dialogue","title":"Visual Dialogue without Vision or Dialogue","date":"2018-12-16","arxiv_id":"1812.06417","repositories_listed":2,"syntology":null},{"url":"/paper/hawk-learning-to-understand-open-world-video","slug":"hawk-learning-to-understand-open-world-video","title":"Hawk: Learning to Understand Open-World Video Anomalies","date":"2024-05-27","arxiv_id":"2405.16886","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hawk-learning-to-understand-open-world-video#ran","syntology_url":"https://syntology.ai/paper/2405.16886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16886"}},"official":{"repos":["jqtangust/hawk"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/collecting-visually-grounded-dialogue-with-a-1","slug":"collecting-visually-grounded-dialogue-with-a-1","title":"Collecting Visually-Grounded Dialogue with A Game Of Sorts","date":"2023-09-10","arxiv_id":"2309.05162","repositories_listed":1,"syntology":null},{"url":"/paper/pace-unified-multi-modal-dialogue-pre","slug":"pace-unified-multi-modal-dialogue-pre","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","date":"2023-05-24","arxiv_id":"2305.14839","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/pace-unified-multi-modal-dialogue-pre#ran","syntology_url":"https://syntology.ai/paper/2305.14839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14839"}},"official":{"repos":["AlibabaResearch/DAMO-ConvAI"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/unified-multimodal-model-with-unlikelihood","slug":"unified-multimodal-model-with-unlikelihood","title":"Unified Multimodal Model with Unlikelihood Training for Visual Dialog","date":"2022-11-23","arxiv_id":"2211.13235","repositories_listed":1,"syntology":null},{"url":"/paper/lavis-a-library-for-language-vision","slug":"lavis-a-library-for-language-vision","title":"LAVIS: A Library for Language-Vision Intelligence","date":"2022-09-15","arxiv_id":"2209.09019","repositories_listed":1,"syntology":null},{"url":"/paper/video-dialog-as-conversation-about-objects","slug":"video-dialog-as-conversation-about-objects","title":"Video Dialog as Conversation about Objects Living in Space-Time","date":"2022-07-08","arxiv_id":"2207.03656","repositories_listed":1,"syntology":null},{"url":"/paper/vd-pcr-improving-visual-dialog-with-pronoun","slug":"vd-pcr-improving-visual-dialog-with-pronoun","title":"VD-PCR: Improving Visual Dialog with Pronoun Coreference Resolution","date":"2022-05-29","arxiv_id":"2205.14693","repositories_listed":1,"syntology":null},{"url":"/paper/spot-the-difference-a-cooperative-object-1","slug":"spot-the-difference-a-cooperative-object-1","title":"Spot the Difference: A Cooperative Object-Referring Game in Non-Perfectly Co-Observable Scene","date":"2022-03-16","arxiv_id":"2203.08362","repositories_listed":1,"syntology":null},{"url":"/paper/uniter-based-situated-coreference-resolution","slug":"uniter-based-situated-coreference-resolution","title":"UNITER-Based Situated Coreference Resolution with Rich Multimodal Input","date":"2021-12-07","arxiv_id":"2112.03521","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-visual-dialog-questioner-with","slug":"enhancing-visual-dialog-questioner-with","title":"Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser","date":"2021-09-06","arxiv_id":"2109.02297","repositories_listed":1,"syntology":null},{"url":"/paper/seqdialn-sequential-visual-dialog-network-in","slug":"seqdialn-sequential-visual-dialog-network-in","title":"SeqDialN: Sequential Visual Dialog Network in Joint Visual-Linguistic Representation Space","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-better-visual-dialog-agents-with","slug":"learning-better-visual-dialog-agents-with","title":"Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation","date":"2021-05-24","arxiv_id":"2105.11541","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual","slug":"ensemble-of-mrr-and-ndcg-models-for-visual","title":"Ensemble of MRR and NDCG models for Visual Dialog","date":"2021-04-15","arxiv_id":"2104.07511","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ensemble-of-mrr-and-ndcg-models-for-visual#ran","syntology_url":"https://syntology.ai/paper/2104.07511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.07511"}},"official":{"repos":["idansc/mrr-ndcg"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/answer-driven-visual-state-estimator-for-goal","slug":"answer-driven-visual-state-estimator-for-goal","title":"Answer-Driven Visual State Estimator for Goal-Oriented Visual Dialogue","date":"2020-10-01","arxiv_id":"2010.00361","repositories_listed":1,"syntology":null},{"url":"/paper/seqdialn-sequential-visual-dialog-networks-in","slug":"seqdialn-sequential-visual-dialog-networks-in","title":"SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space","date":"2020-08-02","arxiv_id":"2008.00397","repositories_listed":1,"syntology":null},{"url":"/paper/dialog-without-dialog-data-learning-visual","slug":"dialog-without-dialog-data-learning-visual","title":"Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data","date":"2020-07-24","arxiv_id":"2007.12750","repositories_listed":1,"syntology":null},{"url":"/paper/multi-view-attention-networks-for-visual","slug":"multi-view-attention-networks-for-visual","title":"Multi-View Attention Network for Visual Dialog","date":"2020-04-29","arxiv_id":"2004.14025","repositories_listed":1,"syntology":null},{"url":"/paper/vd-bert-a-unified-vision-and-dialog","slug":"vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","date":"2020-04-28","arxiv_id":"2004.13278","repositories_listed":1,"syntology":{"n":11,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/vd-bert-a-unified-vision-and-dialog#ran","syntology_url":"https://syntology.ai/paper/2004.13278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.13278"}},"official":{"repos":["salesforce/VD-BERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/dialgraph-sparse-graph-learning-networks-for","slug":"dialgraph-sparse-graph-learning-networks-for","title":"Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer","date":"2020-04-14","arxiv_id":"2004.06698","repositories_listed":1,"syntology":null},{"url":"/paper/iterative-context-aware-graph-inference-for","slug":"iterative-context-aware-graph-inference-for","title":"Iterative Context-Aware Graph Inference for Visual Dialog","date":"2020-04-05","arxiv_id":"2004.02194","repositories_listed":1,"syntology":null},{"url":"/paper/dmrm-a-dual-channel-multi-hop-reasoning-model","slug":"dmrm-a-dual-channel-multi-hop-reasoning-model","title":"DMRM: A Dual-channel Multi-hop Reasoning Model for Visual Dialog","date":"2019-12-18","arxiv_id":"1912.08360","repositories_listed":1,"syntology":null},{"url":"/paper/tab-vcr-tags-and-attributes-based-vcr-1","slug":"tab-vcr-tags-and-attributes-based-vcr-1","title":"TAB-VCR: Tags and Attributes based VCR Baselines","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/efficient-attention-mechanism-for-handling","slug":"efficient-attention-mechanism-for-handling","title":"Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs","date":"2019-11-26","arxiv_id":"1911.11390","repositories_listed":1,"syntology":null},{"url":"/paper/two-causal-principles-for-improving-visual","slug":"two-causal-principles-for-improving-visual","title":"Two Causal Principles for Improving Visual Dialog","date":"2019-11-24","arxiv_id":"1911.10496","repositories_listed":1,"syntology":null},{"url":"/paper/an-annotated-corpus-of-reference-resolution","slug":"an-annotated-corpus-of-reference-resolution","title":"An Annotated Corpus of Reference Resolution for Interpreting Common Grounding","date":"2019-11-18","arxiv_id":"1911.07588","repositories_listed":1,"syntology":null},{"url":"/paper/dualvd-an-adaptive-dual-encoding-model-for","slug":"dualvd-an-adaptive-dual-encoding-model-for","title":"DualVD: An Adaptive Dual Encoding Model for Deep Visual Understanding in Visual Dialogue","date":"2019-11-17","arxiv_id":"1911.07251","repositories_listed":1,"syntology":null},{"url":"/paper/visual-dialogue-state-tracking-for-question","slug":"visual-dialogue-state-tracking-for-question","title":"Visual Dialogue State Tracking for Question Generation","date":"2019-11-12","arxiv_id":"1911.07928","repositories_listed":1,"syntology":null},{"url":"/paper/tab-vcr-tags-and-attributes-based-vcr","slug":"tab-vcr-tags-and-attributes-based-vcr","title":"TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines","date":"2019-10-31","arxiv_id":"1910.14671","repositories_listed":1,"syntology":null},{"url":"/paper/190910470","slug":"190910470","title":"Improving Generative Visual Dialog by Answering Diverse Questions","date":"2019-09-23","arxiv_id":"1909.10470","repositories_listed":1,"syntology":null},{"url":"/paper/factor-graph-attention","slug":"factor-graph-attention","title":"Factor Graph Attention","date":"2019-04-11","arxiv_id":"1904.05880","repositories_listed":1,"syntology":null},{"url":"/paper/reasoning-visual-dialogs-with-structural-and","slug":"reasoning-visual-dialogs-with-structural-and","title":"Reasoning Visual Dialogs with Structural and Partial Observations","date":"2019-04-11","arxiv_id":"1904.05548","repositories_listed":1,"syntology":null},{"url":"/paper/clevr-dialog-a-diagnostic-dataset-for-multi","slug":"clevr-dialog-a-diagnostic-dataset-for-multi","title":"CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog","date":"2019-03-07","arxiv_id":"1903.03166","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clevr-dialog-a-diagnostic-dataset-for-multi#ran","syntology_url":"https://syntology.ai/paper/1903.03166","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.03166"}},"official":{"repos":["satwikkottur/clevr-dialog"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-discourse-parsing","slug":"visual-discourse-parsing","title":"Discourse Parsing in Videos: A Multi-modal Appraoch","date":"2019-03-06","arxiv_id":"1903.02252","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-answerer-in-questioners-mind-for","slug":"large-scale-answerer-in-questioners-mind-for","title":"Large-Scale Answerer in Questioner's Mind for Visual Dialog Question Generation","date":"2019-02-22","arxiv_id":"1902.08355","repositories_listed":1,"syntology":null},{"url":"/paper/recursive-visual-attention-in-visual-dialog","slug":"recursive-visual-attention-in-visual-dialog","title":"Recursive Visual Attention in Visual Dialog","date":"2018-12-06","arxiv_id":"1812.02664","repositories_listed":1,"syntology":null},{"url":"/paper/visual-coreference-resolution-in-visual","slug":"visual-coreference-resolution-in-visual","title":"Visual Coreference Resolution in Visual Dialog using Neural Module Networks","date":"2018-09-06","arxiv_id":"1809.01816","repositories_listed":1,"syntology":null},{"url":"/paper/visual-reasoning-with-multi-hop-feature","slug":"visual-reasoning-with-multi-hop-feature","title":"Visual Reasoning with Multi-hop Feature Modulation","date":"2018-08-03","arxiv_id":"1808.04446","repositories_listed":1,"syntology":null},{"url":"/paper/learning-goal-oriented-visual-dialog-via","slug":"learning-goal-oriented-visual-dialog-via","title":"Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient","date":"2018-07-02","arxiv_id":"1807.00737","repositories_listed":1,"syntology":null},{"url":"/paper/ask-no-more-deciding-when-to-guess-in","slug":"ask-no-more-deciding-when-to-guess-in","title":"Ask No More: Deciding when to guess in referential visual dialogue","date":"2018-05-17","arxiv_id":"1805.06960","repositories_listed":1,"syntology":null},{"url":"/paper/dialog-based-interactive-image-retrieval","slug":"dialog-based-interactive-image-retrieval","title":"Dialog-based Interactive Image Retrieval","date":"2018-05-01","arxiv_id":"1805.00145","repositories_listed":1,"syntology":null},{"url":"/paper/answerer-in-questioners-mind-information","slug":"answerer-in-questioners-mind-information","title":"Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog","date":"2018-02-12","arxiv_id":"1802.03881","repositories_listed":1,"syntology":null},{"url":"/paper/examining-cooperation-in-visual-dialog-models","slug":"examining-cooperation-in-visual-dialog-models","title":"Examining Cooperation in Visual Dialog Models","date":"2017-12-04","arxiv_id":"1712.01329","repositories_listed":1,"syntology":null},{"url":"/paper/best-of-both-worlds-transferring-knowledge","slug":"best-of-both-worlds-transferring-knowledge","title":"Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model","date":"2017-06-05","arxiv_id":"1706.01554","repositories_listed":1,"syntology":null},{"url":"/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","repositories_listed":1,"syntology":null},{"url":null,"slug":"v-2-dial-unification-of-video-and-visual","title":"V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts","date":"2025-03-03","arxiv_id":"2503.02063","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-2dial-unification-of-video-and-visual","title":"V^2Dial: Unification of Video and Visual Dialog via Multimodal Experts","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-visual-dialog-state-tracking","title":"Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations","date":"2024-08-13","arxiv_id":"2408.06725","repositories_listed":0,"syntology":null},{"url":null,"slug":"iccv23-visual-dialog-emotion-explanation","title":"ICCV23 Visual-Dialog Emotion Explanation Challenge: SEU_309 Team Technical Report","date":"2024-07-13","arxiv_id":"2407.09760","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcap-generating-rich-localized-and","title":"FlexCap: Describe Anything in Images in Controllable Detail","date":"2024-03-18","arxiv_id":"2403.12026","repositories_listed":0,"syntology":null},{"url":null,"slug":"mathbb-vd-mathbb-gr-boosting-mathbb-v-isual","title":"$\\mathbb{VD}$-$\\mathbb{GR}$: Boosting $\\mathbb{V}$isual $\\mathbb{D}$ialog with Cascaded Spatial-Temporal Multi-Modal $\\mathbb{GR}$aphs","date":"2023-10-25","arxiv_id":"2310.16590","repositories_listed":0,"syntology":null},{"url":null,"slug":"affective-visual-dialog-a-large-scale","title":"Affective Visual Dialog: A Large-Scale Benchmark for Emotional Reasoning Based on Visually Grounded Conversations","date":"2023-08-30","arxiv_id":"2308.16349","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-knowledge-enhanced-multimodal","title":"A survey on knowledge-enhanced multimodal learning","date":"2022-11-19","arxiv_id":"2211.12328","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-transfer-with-visual-prompt-in","title":"Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-robustness-of-visual-dialog","title":"Adversarial Robustness of Visual Dialog","date":"2022-07-06","arxiv_id":"2207.02639","repositories_listed":0,"syntology":null},{"url":null,"slug":"enrich4all-a-first-luxembourgish-bert-model","title":"ENRICH4ALL: A First Luxembourgish BERT Model for a Multilingual Chatbot","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"utc-a-unified-transformer-with-inter-task","title":"UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog","date":"2022-05-01","arxiv_id":"2205.00423","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-modal-understanding-in-visual","title":"Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning","date":"2022-04-15","arxiv_id":"2204.07302","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-with-multi-structure-commonsense","title":"Reasoning with Multi-Structure Commonsense Knowledge in Visual Dialog","date":"2022-04-10","arxiv_id":"2204.04680","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-coreference-relations-in-visual-1","title":"Modeling Coreference Relations in Visual Dialog","date":"2022-03-06","arxiv_id":"2203.02986","repositories_listed":0,"syntology":null},{"url":null,"slug":"vu-bert-a-unified-framework-for-visual-dialog","title":"VU-BERT: A Unified framework for Visual Dialog","date":"2022-02-22","arxiv_id":"2202.10787","repositories_listed":0,"syntology":null},{"url":null,"slug":"discourse-analysis-for-evaluating-coherence","title":"Discourse Analysis for Evaluating Coherence in Video Paragraph Captions","date":"2022-01-17","arxiv_id":"2201.06207","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-to-fool-systems-and-humans-in-visually","title":"How to Fool Systems and Humans in Visually Grounded Interaction: A Case Study on Adversarial Attacks on Visual Dialog","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enriching-language-models-with-visually","title":"Enriching Language Models with Visually-grounded Word Vectors and the Lancaster Sensorimotor Norms","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"region-under-discussion-for-visual-dialog","title":"Region under Discussion for visual dialog","date":"2021-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vida-man-visual-dialog-with-digital-humans","title":"ViDA-MAN: Visual Dialog with Digital Humans","date":"2021-10-26","arxiv_id":"2110.13384","repositories_listed":0,"syntology":null},{"url":null,"slug":"come-again-re-query-in-referring-expression","title":"Evaluating and Improving Interactions with Hazy Oracles","date":"2021-10-19","arxiv_id":"2110.10206","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-answers-in-referential-visual","title":"The Impact of Answers in Referential Visual Dialog","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-disentangled-attention-for","title":"Variational Disentangled Attention for Regularized Visual Dialog","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gog-relation-aware-graph-over-graph-network","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","date":"2021-09-17","arxiv_id":"2109.08475","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-ground-visual-objects-for-visual","title":"Learning to Ground Visual Objects for Visual Dialog","date":"2021-09-13","arxiv_id":"2109.06013","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-textual-alignment-for-graph-inference","title":"Visual-Textual Alignment for Graph Inference in Visual Dialog","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-over-history-context-aware-visual","title":"Reasoning Over History: Context Aware Visual Dialog","date":"2020-11-02","arxiv_id":"2011.00669","repositories_listed":0,"syntology":null},{"url":"/paper/multi-modal-open-domain-dialogue","slug":"multi-modal-open-domain-dialogue","title":"Multi-Modal Open-Domain Dialogue","date":"2020-10-02","arxiv_id":"2010.01082","repositories_listed":0,"syntology":null},{"url":null,"slug":"effective-questions-in-referential-visual","title":"Effective questions in referential visual dialogue","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-visual-dialog-for-radiology","title":"Towards Visual Dialog for Radiology","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ord-object-relationship-discovery-for-visual","title":"ORD: Object Relationship Discovery for Visual Dialogue Generation","date":"2020-06-15","arxiv_id":"2006.08322","repositories_listed":0,"syntology":null},{"url":null,"slug":"modality-balanced-models-for-visual-dialogue","title":"Modality-Balanced Models for Visual Dialogue","date":"2020-01-17","arxiv_id":"2001.06354","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-based-discriminative-models-for","title":"Ensemble based discriminative models for Visual Dialog Challenge 2018","date":"2020-01-15","arxiv_id":"2001.05865","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-and-language-from-visual-perception-to","title":"Vision and Language: from Visual Perception to Content Creation","date":"2019-12-26","arxiv_id":"1912.11872","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-dialog-via-progressive-inference-and","title":"Video Dialog via Progressive Inference and Cross-Transformer","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"granular-multimodal-attention-networks-for","title":"Granular Multimodal Attention Networks for Visual Dialog","date":"2019-10-13","arxiv_id":"1910.05728","repositories_listed":0,"syntology":null},{"url":null,"slug":"190909964","title":"On Controlled DeEntanglement for Natural Language Processing","date":"2019-09-22","arxiv_id":"1909.09964","repositories_listed":0,"syntology":null},{"url":"/paper/probabilistic-framework-for-solving-visual","slug":"probabilistic-framework-for-solving-visual","title":"Probabilistic framework for solving Visual Dialog","date":"2019-09-11","arxiv_id":"1909.04800","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-task-oriented-visual-dialog-systems","title":"Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation","date":"2019-09-06","arxiv_id":"1909.05365","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-agreement-games-emphasizing","title":"Grounded Agreement Games: Emphasizing Conversational Grounding in Visual Dialogue Settings","date":"2019-08-29","arxiv_id":"1908.11279","repositories_listed":0,"syntology":null},{"url":null,"slug":"reactive-multi-stage-feature-fusion-for","title":"Reactive Multi-Stage Feature Fusion for Multimodal Dialogue Modeling","date":"2019-08-14","arxiv_id":"1908.05067","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-should-i-ask-using-conversationally-1","title":"What Should I Ask? Using Conversationally Informative Rewards for Goal-Oriented Visual Dialog","date":"2019-07-28","arxiv_id":"1907.12021","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-goal-oriented-visual-dialog-agents","title":"Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts","date":"2019-07-24","arxiv_id":"1907.10500","repositories_listed":0,"syntology":null}],"syntology_records":12,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/visual-dialogue/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/visual-dialogue/papers/2","json":"/task/visual-dialogue/papers/2.json","rows":18},{"order":"ran","page":1,"of":1,"url":"/task/visual-dialogue/papers/ran/1","json":"/task/visual-dialogue/papers/ran/1.json","rows":11}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"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"},"record_sha256":"d87b6679aa63a9ec4f58f7892532950b9e5e58446deddf341d7ec1f94d7fd0a4","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}