{"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":"/sota/visual-reasoning-on-winoground","task":{"name":"Visual Reasoning","url":"/task/visual-reasoning","note":null},"dataset":{"name":"Winoground","url":"/dataset/winoground"},"category":"Computer Vision","categories":["Computer Vision","Reasoning"],"category_note":null,"description":"Ability to understand  actions and reasoning  associated with any  visual images","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Text Score","Image Score","Group Score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction; the tokens 'score' and 'time' are not used on this page); null = not inferred, chart draws points only","by_metric":{"Text Score":null,"Image Score":null,"Group Score":null}},"counts":{"rows":114,"rows_with_code":78,"rows_with_paper_page":111,"rows_dated":111,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GPT-4o + CA","metrics":{"Group Score":"52","Image Score":"58.5","Text Score":"75.5"},"uses_additional_data":false,"paper_date":"2025-01-23","paper":"/paper/cognitive-paradigms-for-evaluating-vlms-on","paper_url":"https://arxiv.org/abs/2501.13620v5","paper_title":"A Cognitive Paradigm Approach to Probe the Perception-Reasoning Interface in VLMs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":2,"model":"GPT-4V (CoT, pick b/w two options)","metrics":{"Group Score":"58.75","Image Score":"68.75","Text Score":"75.25"},"uses_additional_data":false,"paper_date":"2023-11-15","paper":"/paper/the-role-of-chain-of-thought-in-complex","paper_url":"https://arxiv.org/abs/2311.09193v1","paper_title":"The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":3,"model":"GPT-4V (pick b/w two options)","metrics":{"Group Score":"39.25","Image Score":"46.25","Text Score":"69.25"},"uses_additional_data":false,"paper_date":"2023-11-15","paper":"/paper/the-role-of-chain-of-thought-in-complex","paper_url":"https://arxiv.org/abs/2311.09193v1","paper_title":"The Role of Chain-of-Thought in Complex Vision-Language Reasoning Task","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":4,"model":"MMICL + CoCoT","metrics":{"Group Score":"50.75","Image Score":"52.5","Text Score":"64.25"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":5,"model":"GPT-4V + CoCoT","metrics":{"Group Score":"44.5","Image Score":"49.5","Text Score":"58.5"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":6,"model":"OpenFlamingo + CoCoT","metrics":{"Group Score":"41.5","Image Score":"55.25","Text Score":"58.25"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":7,"model":"GPT-4V","metrics":{"Group Score":"37.75","Image Score":"42.5","Text Score":"54.5"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":8,"model":"FIBER (EqSim)","metrics":{"Group Score":"27.5","Image Score":"32.00","Text Score":"51.5"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":9,"model":"FIBER (finetuned, Flickr30k)","metrics":{"Group Score":"23.00","Image Score":"26.50","Text Score":"51.25"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":10,"model":"MMICL + CCoT","metrics":{"Group Score":"47.5","Image Score":"48","Text Score":"51"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":11,"model":"OpenFlamingo + DDCoT","metrics":{"Group Score":"39","Image Score":"47.25","Text Score":"47.5"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":12,"model":"VQ2","metrics":{"Group Score":"30.5","Image Score":"42.2","Text Score":"47"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":13,"model":"MMICL + DDCoT","metrics":{"Group Score":"36.75","Image Score":"45","Text Score":"46.75"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":14,"model":"X-VLM 16M","metrics":{"Group Score":"21.2","Image Score":"24.5","Text Score":"46.7"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":15,"model":"PaLI (ft SNLI-VE + Synthetic Data)","metrics":{"Group Score":"28.75","Image Score":"38","Text Score":"46.5"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":16,"model":"FIBER","metrics":{"Group Score":"22.25","Image Score":"25.75","Text Score":"46.25"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":17,"model":"MMICL (FLAN-T5-XXL)","metrics":{"Group Score":"43.00","Image Score":"44.99","Text Score":"45.50"},"uses_additional_data":false,"paper_date":"2023-09-14","paper":"/paper/mmicl-empowering-vision-language-model-with","paper_url":"https://arxiv.org/abs/2309.07915v3","paper_title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","code":"https://github.com/haozhezhao/mic","n_code_links":2,"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"syntology":{"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_samples":7,"n_pointer_only_licence":7,"sample_list":"/paper/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}}}},{"rank_in_archive_order":18,"model":"PaLI (ft SNLI-VE)","metrics":{"Group Score":"28.70","Image Score":"41.50","Text Score":"45.00"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":19,"model":"Gemini + DDCoT","metrics":{"Group Score":"23.75","Image Score":"25","Text Score":"45"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":20,"model":"METER (EqSim)","metrics":{"Group Score":"18.75","Image Score":"22.75","Text Score":"45.0"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":21,"model":"X-VLM 4M","metrics":{"Group Score":"21.5","Image Score":"26.7","Text Score":"44.0"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":22,"model":"BLIP2 (ft COCO)","metrics":{"Group Score":"23.50","Image Score":"26.00","Text Score":"44.00"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":23,"model":"KeyComp* (GPT-4)","metrics":{"Group Score":"18.2","Image Score":"28.7","Text Score":"43.5"},"uses_additional_data":false,"paper_date":"2024-01-20","paper":"/paper/prompting-large-vision-language-models-for","paper_url":"https://arxiv.org/abs/2401.11337v1","paper_title":"Prompting Large Vision-Language Models for Compositional Reasoning","code":"https://github.com/tossowski/keycomp","n_code_links":1,"official":{"repos":["tossowski/keycomp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/prompting-large-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.11337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11337"}}}},{"rank_in_archive_order":24,"model":"METER (finetuned, Flickr30k)","metrics":{"Group Score":"14.75","Image Score":"20.75","Text Score":"43.5"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":25,"model":"BLIP2 (SGVL)","metrics":{"Group Score":"23.3","Image Score":"28.5","Text Score":"42.8"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":26,"model":"BLIP (SGVL)","metrics":{"Group Score":"21.5","Image Score":"27.3","Text Score":"42.8"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":27,"model":"KeyComp* (GPT-3.5)","metrics":{"Group Score":"17.4","Image Score":"27.8","Text Score":"42.7"},"uses_additional_data":false,"paper_date":"2024-01-20","paper":"/paper/prompting-large-vision-language-models-for","paper_url":"https://arxiv.org/abs/2401.11337v1","paper_title":"Prompting Large Vision-Language Models for Compositional Reasoning","code":"https://github.com/tossowski/keycomp","n_code_links":1,"official":{"repos":["tossowski/keycomp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/prompting-large-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.11337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11337"}}}},{"rank_in_archive_order":28,"model":"OpenFlamingo + CCoT","metrics":{"Group Score":"20","Image Score":"27.5","Text Score":"42.5"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":29,"model":"NegBLIP","metrics":{"Group Score":"18.5","Image Score":"24.0","Text Score":"42.5"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":30,"model":"IAIS large (Flickr30k)","metrics":{"Group Score":"16.00","Image Score":"19.75","Text Score":"42.50"},"uses_additional_data":false,"paper_date":"2022-12-03","paper":"/paper/does-structural-attention-improve","paper_url":"https://sslneurips22.github.io/paper_pdfs/paper_65.pdf","paper_title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":31,"model":"LLaVA-1.5-CCoT","metrics":{"Group Score":"22.3","Image Score":"35.5","Text Score":"42.0"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"rank_in_archive_order":32,"model":"BLIP2","metrics":{"Group Score":"19.0","Image Score":"23.8","Text Score":"42.0"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":33,"model":"IAIS large (COCO)","metrics":{"Group Score":"15.50","Image Score":"19.75","Text Score":"41.75"},"uses_additional_data":false,"paper_date":"2022-12-03","paper":"/paper/does-structural-attention-improve","paper_url":"https://sslneurips22.github.io/paper_pdfs/paper_65.pdf","paper_title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":34,"model":"NegBLIP2","metrics":{"Group Score":"20.5","Image Score":"26.0","Text Score":"41.5"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":35,"model":"BLIP (+Graph Text, +Graph Neg)","metrics":{"Group Score":"19.0","Image Score":"25.5","Text Score":"40.5"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":36,"model":"BLIP (+Graph Text)","metrics":{"Group Score":"16.5","Image Score":"20.5","Text Score":"40.3"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":37,"model":"Gemini + CoCoT","metrics":{"Group Score":"27.75","Image Score":"32.5","Text Score":"40"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":38,"model":"CACR base","metrics":{"Group Score":"14.25","Image Score":"17.75","Text Score":"39.25"},"uses_additional_data":false,"paper_date":"2022-12-03","paper":"/paper/does-structural-attention-improve","paper_url":"https://sslneurips22.github.io/paper_pdfs/paper_65.pdf","paper_title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":39,"model":"METER","metrics":{"Group Score":"12.00","Image Score":"15.75","Text Score":"39.25"},"uses_additional_data":false,"paper_date":"2023-03-25","paper":"/paper/equivariant-similarity-for-vision-language","paper_url":"https://arxiv.org/abs/2303.14465v2","paper_title":"Equivariant Similarity for Vision-Language Foundation Models","code":"https://github.com/wangt-cn/eqben","n_code_links":1,"official":{"repos":["wangt-cn/eqben"],"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"]},"syntology":{"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0,"sample_list":"/paper/equivariant-similarity-for-vision-language#ran","syntology_url":"https://syntology.ai/paper/2303.14465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.14465"}}}},{"rank_in_archive_order":40,"model":"OpenFlamingo","metrics":{"Group Score":"33.25","Image Score":"41.25","Text Score":"39"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":41,"model":"BLIP","metrics":{"Group Score":"15.0","Image Score":"19.2","Text Score":"39.0"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":42,"model":"GPT-4V (image-caption match answer yes/no, zero-shot)","metrics":{"Group Score":"38.00","Image Score":"38.00","Text Score":"38.00"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":43,"model":"UNITER large","metrics":{"Group Score":"10.50","Image Score":"14.00","Text Score":"38.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":44,"model":"VinVL","metrics":{"Group Score":"14.50","Image Score":"17.75","Text Score":"37.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":45,"model":"ViLLA large","metrics":{"Group Score":"11.00","Image Score":"13.25","Text Score":"37.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":46,"model":"BLIP (VisualGPTScore, α-tuned)","metrics":{"Group Score":"16.8","Image Score":"21.5","Text Score":"36.5"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/visualgptscore-visio-linguistic-reasoning","paper_url":"https://arxiv.org/abs/2306.01879v4","paper_title":"Revisiting the Role of Language Priors in Vision-Language Models","code":"https://github.com/linzhiqiu/visual_gpt_score","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":47,"model":"BLIP 14M","metrics":{"Group Score":"14.5","Image Score":"18.5","Text Score":"36.5"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":48,"model":"ViT-B/16 + BERT base + ViLEM","metrics":{"Text Score":"36.5"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/vilem-visual-language-error-modeling-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Chen_ViLEM_Visual-Language_Error_Modeling_for_Image-Text_Retrieval_CVPR_2023_paper.html","paper_title":"ViLEM: Visual-Language Error Modeling for Image-Text Retrieval","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":49,"model":"LLaVA-1.5","metrics":{"Group Score":"20.1","Image Score":"33.3","Text Score":"36.0"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"rank_in_archive_order":50,"model":"BLIP (ITM)","metrics":{"Group Score":"13.3","Image Score":"15.8","Text Score":"35.8"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/visualgptscore-visio-linguistic-reasoning","paper_url":"https://arxiv.org/abs/2306.01879v4","paper_title":"Revisiting the Role of Language Priors in Vision-Language Models","code":"https://github.com/linzhiqiu/visual_gpt_score","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":51,"model":"BLIP 129M","metrics":{"Group Score":"11.7","Image Score":"15.0","Text Score":"35.5"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":52,"model":"ROSITA (Flickr30k)","metrics":{"Group Score":"12.25","Image Score":"15.25","Text Score":"35.25"},"uses_additional_data":false,"paper_date":"2022-12-03","paper":"/paper/does-structural-attention-improve","paper_url":"https://sslneurips22.github.io/paper_pdfs/paper_65.pdf","paper_title":"Does Structural Attention Improve Compositional Representations in Vision-Language Models?","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":53,"model":"ViLT (ViT-B/32)","metrics":{"Group Score":"9.25","Image Score":"14.00","Text Score":"34.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":54,"model":"BLIP 129M (CapFilt/L)","metrics":{"Group Score":"12.2","Image Score":"15.2","Text Score":"34.7"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":55,"model":"BLIP-ViT/L 129M","metrics":{"Group Score":"12.2","Image Score":"14.5","Text Score":"34.7"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":56,"model":"Diffusion Classifier (zero-shot)","metrics":{"Text Score":"34.00"},"uses_additional_data":false,"paper_date":"2023-03-28","paper":"/paper/your-diffusion-model-is-secretly-a-zero-shot","paper_url":"https://arxiv.org/abs/2303.16203v3","paper_title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","code":"https://github.com/diffusion-classifier/diffusion-classifier","n_code_links":4,"official":{"repos":["diffusion-classifier/diffusion-classifier"],"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"]},"syntology":{"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":1,"sample_list":"/paper/your-diffusion-model-is-secretly-a-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2303.16203","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16203"}}}},{"rank_in_archive_order":57,"model":"PEVL 14M","metrics":{"Group Score":"12.2","Image Score":"15.7","Text Score":"33.2"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":58,"model":"ALBEF 14M","metrics":{"Group Score":"12.7","Image Score":"16.2","Text Score":"32.5"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":59,"model":"FLAVA (ITM)","metrics":{"Group Score":"14.25","Image Score":"20.50","Text Score":"32.25"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":60,"model":"UNITER base","metrics":{"Group Score":"10.00","Image Score":"13.25","Text Score":"32.25"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":61,"model":"CLIP (SGVL)","metrics":{"Group Score":"9.8","Image Score":"14.0","Text Score":"32.0"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":62,"model":"ViT-B/16 + BERT base","metrics":{"Text Score":"31.2"},"uses_additional_data":false,"paper_date":"2023-01-01","paper":"/paper/vilem-visual-language-error-modeling-for","paper_url":"http://openaccess.thecvf.com//content/CVPR2023/html/Chen_ViLEM_Visual-Language_Error_Modeling_for_Image-Text_Retrieval_CVPR_2023_paper.html","paper_title":"ViLEM: Visual-Language Error Modeling for Image-Text Retrieval","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":63,"model":"Gemini","metrics":{"Group Score":"25","Image Score":"26","Text Score":"30.75"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":64,"model":"OCLIP (ViT-H/14)","metrics":{"Image Score":"12.75","Text Score":"30.75"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":65,"model":"CLIP (ViT-B/32)","metrics":{"Group Score":"8.00","Image Score":"10.50","Text Score":"30.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":66,"model":"OFA large (ITM)","metrics":{"Group Score":"7.25","Image Score":"10.25","Text Score":"30.75"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":67,"model":"KeyComp (GPT-3.5)","metrics":{"Group Score":"12.4","Image Score":"24.6","Text Score":"30.3"},"uses_additional_data":false,"paper_date":"2024-01-20","paper":"/paper/prompting-large-vision-language-models-for","paper_url":"https://arxiv.org/abs/2401.11337v1","paper_title":"Prompting Large Vision-Language Models for Compositional Reasoning","code":"https://github.com/tossowski/keycomp","n_code_links":1,"official":{"repos":["tossowski/keycomp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":2,"sample_list":"/paper/prompting-large-vision-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2401.11337","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11337"}}}},{"rank_in_archive_order":68,"model":"CLIP (ViT-L/14)","metrics":{"Image Score":"8.0","Text Score":"30.25"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":69,"model":"ViLLA base","metrics":{"Group Score":"8.00","Image Score":"12.00","Text Score":"30.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":70,"model":"syn-CLIP","metrics":{"Group Score":"9.50","Image Score":"11.50","Text Score":"30.00"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/going-beyond-nouns-with-vision-language","paper_url":"https://arxiv.org/abs/2303.17590v2","paper_title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","code":"https://github.com/uvavision/syvic","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":71,"model":"syn-CyCLIP","metrics":{"Group Score":"8.25","Image Score":"10.75","Text Score":"30.00"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/going-beyond-nouns-with-vision-language","paper_url":"https://arxiv.org/abs/2303.17590v2","paper_title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","code":"https://github.com/uvavision/syvic","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":72,"model":"NegCLIP","metrics":{"Group Score":"8.0","Image Score":"10.5","Text Score":"29.5"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":73,"model":"OFA large (TLC-A)","metrics":{"Group Score":"17.50","Image Score":"27.00","Text Score":"29.25"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":74,"model":"ALBEF 4M","metrics":{"Group Score":"11.0","Image Score":"15.5","Text Score":"29.2"},"uses_additional_data":false,"paper_date":"2023-05-12","paper":"/paper/measuring-progress-in-fine-grained-vision-and","paper_url":"https://arxiv.org/abs/2305.07558v1","paper_title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","code":"https://github.com/e-bug/fine-grained-evals","n_code_links":2,"official":{"repos":["e-bug/fine-grained-evals"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]},"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/measuring-progress-in-fine-grained-vision-and#ran","syntology_url":"https://syntology.ai/paper/2305.07558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.07558"}}}},{"rank_in_archive_order":75,"model":"LDM-T5 (SelfEval)","metrics":{"Image Score":"13.50","Text Score":"29.00"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":76,"model":"CyCLIP","metrics":{"Group Score":"7.25","Image Score":"9.50","Text Score":"28.50"},"uses_additional_data":false,"paper_date":"2023-03-30","paper":"/paper/going-beyond-nouns-with-vision-language","paper_url":"https://arxiv.org/abs/2303.17590v2","paper_title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","code":"https://github.com/uvavision/syvic","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":77,"model":"PDM-T5 (SelfEval)","metrics":{"Image Score":"12.00","Text Score":"28.25"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":78,"model":"COCA ViT-L14 (f.t on COCO)","metrics":{"Group Score":"8.25","Image Score":"11.50","Text Score":"28.25"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":79,"model":"LLaVA-1.5-ZS-CoT","metrics":{"Group Score":"12.3","Image Score":"22.5","Text Score":"28.0"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"rank_in_archive_order":80,"model":"BLIP (ITC)","metrics":{"Group Score":"6.5","Image Score":"9.0","Text Score":"28.0"},"uses_additional_data":false,"paper_date":"2023-06-02","paper":"/paper/visualgptscore-visio-linguistic-reasoning","paper_url":"https://arxiv.org/abs/2306.01879v4","paper_title":"Revisiting the Role of Language Priors in Vision-Language Models","code":"https://github.com/linzhiqiu/visual_gpt_score","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":81,"model":"OFA large (ft SNLI-VE)","metrics":{"Group Score":"9.00","Image Score":"14.30","Text Score":"27.70"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":82,"model":"OFA base (ITM)","metrics":{"Group Score":"6.50","Image Score":"10.75","Text Score":"26.75"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":83,"model":"CLIP RN50x64","metrics":{"Group Score":"10.25","Image Score":"13.75","Text Score":"26.50"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":84,"model":"LLaVA-7B (GPTScore)","metrics":{"Group Score":"10.50","Image Score":"17.00","Text Score":"25.50"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/an-examination-of-the-compositionality-of","paper_url":"https://arxiv.org/abs/2308.10509v2","paper_title":"An Examination of the Compositionality of Large Generative Vision-Language Models","code":"https://github.com/teleema/sade","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":85,"model":"FLAVA (contrastive)","metrics":{"Group Score":"9.00","Image Score":"13.50","Text Score":"25.25"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":86,"model":"Random chance","metrics":{"Group Score":"16.67","Image Score":"25.00","Text Score":"25.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":87,"model":"LLaVA","metrics":{"Group Score":"13.0","Image Score":"25.0","Text Score":"24.8"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":88,"model":"OFA base (TLC-A)","metrics":{"Group Score":"13.75","Image Score":"23.50","Text Score":"24.50"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":89,"model":"MiniGPT-4-7B (GPTScore)","metrics":{"Group Score":"11.50","Image Score":"21.75","Text Score":"24.50"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/an-examination-of-the-compositionality-of","paper_url":"https://arxiv.org/abs/2308.10509v2","paper_title":"An Examination of the Compositionality of Large Generative Vision-Language Models","code":"https://github.com/teleema/sade","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":90,"model":"ViLBERT base","metrics":{"Group Score":"4.75","Image Score":"7.25","Text Score":"23.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":91,"model":"MiniGPT-4","metrics":{"Group Score":"9.5","Image Score":"18.0","Text Score":"23.3"},"uses_additional_data":false,"paper_date":"2023-05-10","paper":"/paper/incorporating-structured-representations-into","paper_url":"https://arxiv.org/abs/2305.06343v2","paper_title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":92,"model":"MiniGPT-4-7B (VisualGPTScore)","metrics":{"Group Score":"9.50","Image Score":"18.00","Text Score":"23.25"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/an-examination-of-the-compositionality-of","paper_url":"https://arxiv.org/abs/2308.10509v2","paper_title":"An Examination of the Compositionality of Large Generative Vision-Language Models","code":"https://github.com/teleema/sade","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":93,"model":"VSE++ (COCO, ResNet)","metrics":{"Group Score":"4.00","Image Score":"8.00","Text Score":"22.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":94,"model":"OFA tiny (ITM)","metrics":{"Group Score":"4.50","Image Score":"7.75","Text Score":"22.75"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":95,"model":"LDM-CLIP (SelfEval)","metrics":{"Image Score":"7.25","Text Score":"22.75"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":96,"model":"Gemini + CCoT","metrics":{"Group Score":"20.75","Image Score":"33","Text Score":"22.5"},"uses_additional_data":false,"paper_date":"2024-01-05","paper":"/paper/cocot-contrastive-chain-of-thought-prompting","paper_url":"https://arxiv.org/abs/2401.02582v1","paper_title":"CoCoT: Contrastive Chain-of-Thought Prompting for Large Multimodal Models with Multiple Image Inputs","code":"https://github.com/vista-h/gpt-4v_social_media","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":97,"model":"InstructBLIP-CCoT","metrics":{"Group Score":"8.3","Image Score":"21.3","Text Score":"21.0"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"rank_in_archive_order":98,"model":"VSRN (Flickr30k)","metrics":{"Group Score":"3.50","Image Score":"5.00","Text Score":"20.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":99,"model":"VSE++ (Flickr30k, ResNet)","metrics":{"Group Score":"2.75","Image Score":"5.00","Text Score":"20.00"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":100,"model":"VSE++ (Flickr30k, VGG)","metrics":{"Group Score":"4.50","Image Score":"6.25","Text Score":"19.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":101,"model":"UniT (ITM finetuned)","metrics":{"Group Score":"4.00","Image Score":"6.25","Text Score":"19.50"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":102,"model":"LXMERT","metrics":{"Group Score":"4.00","Image Score":"7.00","Text Score":"19.25"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":103,"model":"TIFA","metrics":{"Group Score":"11.30","Image Score":"12.50","Text Score":"19.00"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/what-you-see-is-what-you-read-improving-text-1","paper_url":"https://arxiv.org/abs/2305.10400v4","paper_title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","code":"https://github.com/yonatanbitton/wysiwyr","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":104,"model":"IDEFICS 80B","metrics":{"Group Score":"8.0","Image Score":"22.5","Text Score":"18.75"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":105,"model":"VSE++ (COCO, VGG)","metrics":{"Group Score":"3.50","Image Score":"5.50","Text Score":"18.75"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":106,"model":"VSRN (COCO)","metrics":{"Group Score":"3.75","Image Score":"7.00","Text Score":"17.50"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":107,"model":"PDM-CLIP (SelfEval)","metrics":{"Image Score":"14.00","Text Score":"17.00"},"uses_additional_data":false,"paper_date":"2023-11-17","paper":"/paper/selfeval-leveraging-the-discriminative-nature","paper_url":"https://arxiv.org/abs/2311.10708v2","paper_title":"SelfEval: Leveraging the discriminative nature of generative models for evaluation","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":108,"model":"IDEFICS 9B","metrics":{"Group Score":"5.0","Image Score":"20.8","Text Score":"16.8"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":109,"model":"OFA tiny (TLC-A)","metrics":{"Group Score":"6.75","Image Score":"15.75","Text Score":"16.50"},"uses_additional_data":false,"paper_date":"2023-05-11","paper":"/paper/simple-token-level-confidence-improves","paper_url":"https://arxiv.org/abs/2305.07021v1","paper_title":"Simple Token-Level Confidence Improves Caption Correctness","code":null,"n_code_links":0,"official":null,"syntology":null},{"rank_in_archive_order":110,"model":"VisualBERT base","metrics":{"Group Score":"1.50","Image Score":"2.50","Text Score":"15.50"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/winoground-probing-vision-and-language-models","paper_url":"https://arxiv.org/abs/2204.03162v2","paper_title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","code":"https://github.com/wangt-cn/eqben","n_code_links":2,"official":null,"syntology":{"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_samples":4,"n_pointer_only_licence":3,"sample_list":"/paper/winoground-probing-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2204.03162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03162"}}}},{"rank_in_archive_order":111,"model":"MiniGPT-4-7B (BERTScore)","metrics":{"Group Score":"2.75","Image Score":"8.00","Text Score":"14.00"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/an-examination-of-the-compositionality-of","paper_url":"https://arxiv.org/abs/2308.10509v2","paper_title":"An Examination of the Compositionality of Large Generative Vision-Language Models","code":"https://github.com/teleema/sade","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":112,"model":"LLaVA-7B (BERTScore)","metrics":{"Group Score":"2.25","Image Score":"5.25","Text Score":"13.50"},"uses_additional_data":false,"paper_date":"2023-08-21","paper":"/paper/an-examination-of-the-compositionality-of","paper_url":"https://arxiv.org/abs/2308.10509v2","paper_title":"An Examination of the Compositionality of Large Generative Vision-Language Models","code":"https://github.com/teleema/sade","n_code_links":1,"official":null,"syntology":null},{"rank_in_archive_order":113,"model":"InstructBLIP-ZS-CoT","metrics":{"Group Score":"4.0","Image Score":"16.3","Text Score":"9.3"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}},{"rank_in_archive_order":114,"model":"InstructBLIP","metrics":{"Group Score":"3.3","Image Score":"11.5","Text Score":"7.0"},"uses_additional_data":false,"paper_date":"2023-11-27","paper":"/paper/compositional-chain-of-thought-prompting-for","paper_url":"https://arxiv.org/abs/2311.17076v3","paper_title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","code":"https://github.com/chancharikmitra/ccot","n_code_links":1,"official":{"repos":["chancharikmitra/ccot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]},"syntology":{"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1,"sample_list":"/paper/compositional-chain-of-thought-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2311.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17076"}}}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"adjudicator":"Claude Opus 5.5","adjudicator_from":"groundwork/59_code_with_papers/LB_EXTRACTOR_PREREG.md (not recorded in lb_measurement.json; the file's frozen_commit, measured_on and counts equal the run the pre-registration records)","adjudicator_sensitivity":[69,70],"adjudicator_specificity":[101,103],"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication by a model (adjudicator) of accepted entries on a held-out split of archive papers, rules frozen before the test; adjudicator_sensitivity and adjudicator_specificity are its own controls as [judged right, of]; it was not measured on the newer papers placed here","measurement_sentence":"Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.","coverage":{"sentence":"Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.","complete":false,"papers_newer_than_archive":18637,"papers_checked":8886,"papers_checked_no_leaderboard_matched":3717,"papers_read_nothing_to_place":733,"papers_could_not_be_read":41,"papers_could_not_be_read_by_status":{"unparseable":41},"papers_extracted_not_yet_verified":0,"boards_without_verdict":3,"papers_not_yet_extracted":8975},"board_status":{"sentence":"Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 1 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,596 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and none proposed a result, so none await a verdict and none were placed.","note":"papers, from the extractor's own records, over the newer papers whose tables were read; proposed = no_cell_passed_checks + rejected_by_independent_check + accepted_not_placed + awaiting_verdict + placed; counts, never a rate","eligible":true,"eligible_note":"false when the extractor never considers this board: it loads only boards with archive rows and at least one metric column (lb_extract.py Boards), so no newer paper can be proposed here; archive_rows and metric_columns say which","archive_rows":114,"metric_columns":3,"papers_read":8888,"papers_read_checked":8886,"papers_read_awaiting_verdict":2,"papers_read_verified":8888,"papers_read_not_yet_verified":0,"papers_read_at_candidate_cap":1596,"papers_read_list_full_without_this_board":1596,"candidates":1,"candidates_capped_note":"candidates = papers that had this board among the leaderboards the extractor considered for their tables; the extractor keeps at most 10 per paper and 4 per dataset, so a board crowded out of a paper's list is not counted and candidates is a floor; papers_read_list_full_without_this_board counts the read papers whose list did not hold this board and had reached 10, or held 4 boards of this board's dataset (the only papers that could have crowded it out); papers_read_at_candidate_cap counts, over every board, the papers whose list reached 10","proposed":0,"no_cell_passed_checks":0,"rejected_by_independent_check":0,"accepted_not_placed":0,"awaiting_verdict":0,"placed":0,"placed_entries_listed":0,"file_lines_unreadable_as_read":0,"since_line":"Since the archive (Syntology): none placed; no newer paper judged to report on this board so far"},"judged_to_report":{"heading":"Newer papers whose tables a model judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)","judged_by":{"model":"a model","models_as_recorded":[],"a_record_without_a_model":false,"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","order":"newest first by arXiv id (the identifier's order, not a rank)","outcomes":{"placed":"placed","no_cell_passed_checks":"no cell passed the extractor's checks","refused_by_rule":"refused by a rule","rejected":"rejected by the independent check","accepted_not_placed":"accepted by the independent check but not placed by this site","awaiting":"awaiting a verdict"},"reason_note":"for refused_by_rule, the rules' plain words for the reason codes the record gives (never the quoted or the actual cell text); null for every other outcome","total":0,"shown_on_page":0,"no_cell_split":{"no_cell_passed_checks_in_ledger":0,"rows_refused_by_rule":0,"rows_no_cell_passed_checks":0},"rows":[]},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per row: of M harvested code samples from that row's paper, n_ran executed on a synthesized fixture (n_ran = n_ran_checked + n_instrument; n_instrument counts failures of Syntology's instrument, not of the code); the other M - n_ran are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","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)"},"rows_with_graph_line":46,"rows_with_any_sample_ran":46,"rows_with_a_run_with_no_instrument_failure":43,"official":{"state_rule":"the archive's official repositories have samples for this paper that ran: 'official (archive's flag): N ran' (N counts them, instrument failures included); they have samples, none ran: 'official: harvested, nothing ran'; they have no sample for this paper and another sample ran: 'community repositories only' when every sample that ran came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, else 'official: no sample here; runs from other or unrecorded repositories' (a repository named in the paper or found in its text by Syntology, or no repository recorded); otherwise 'official: harvested for another paper' or 'official: not harvested'. Absent when the archive marks no repository official. Official is the archive's is_official flag, not an authorship verdict","flag":"the archive's is_official flag for the paper's code link; not a verdict on who wrote the code","rows_with_an_archive_official_repository":26,"rows_whose_official_repository_has_a_sample_that_ran":26,"rows_whose_official_repository_has_a_run_with_no_instrument_failure":23,"rows_community_repositories_only":0,"rows_runs_from_other_or_unrecorded_repositories":0,"note":"rows[].official, per row with a graph line: repos (marked official in the archive), state, n_ran and n_unverified (samples from those repositories), and ran_from_kinds (the kinds of repository the paper's samples that ran came from; 'unlocated' is no repository recorded)"},"filters":{"ran_modes":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"the page's filters hide rows and never renumber them; they read the Ran cell's counts, the same figures rows[].syntology and rows[].official carry"},"row_route":"rows[].syntology 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","distinct_papers_with_graph_line":7,"distinct_papers_with_any_sample_ran":7,"distinct_papers_with_a_run_with_no_instrument_failure":6,"samples_over_distinct_papers":{"n_ran":20,"n_constructed":1,"n_ran_checked":10,"n_instrument":10,"n_unverified":4,"n_samples":24,"n_pointer_only_licence":15,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":150,"n_constructed":6,"n_ran_checked":93,"n_instrument":57,"n_unverified":11,"n_samples":161,"n_pointer_only_licence":89,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}},"record_sha256":"4898bb88aa33d5f126673585acd33f26bf77097febc4b7826de408f167bbb5b1","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}