{"url":"/task/visual-entailment","name":"Visual Entailment","slug":"visual-entailment","description_markdown":"Visual Entailment (VE) - is a task consisting of image-sentence pairs\r\nwhereby a premise is defined by an image, rather than a\r\nnatural language sentence as in traditional Textual Entailment tasks. The goal is to predict\r\nwhether the image semantically entails the text.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":56,"papers_with_code":33,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":3,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","slug":"visual-entailment-on-snli-ve-val","dataset":"SNLI-VE val","dataset_url":"/dataset/snli-ve","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","paper_url":"/paper/unifying-architectures-tasks-and-modalities","paper_date":"2022-02-07","arxiv_id":"2202.03052","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"},{"title":"JHKim-snu/GVCCI","url":"https://github.com/JHKim-snu/GVCCI"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","slug":"visual-entailment-on-snli-ve-test","dataset":"SNLI-VE test","dataset_url":"/dataset/snli-ve","rows_in_archive":8,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA","paper_title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","paper_url":"/paper/unifying-architectures-tasks-and-modalities","paper_date":"2022-02-07","arxiv_id":"2202.03052","code_links":[{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"ofa-sys/ofa","url":"https://github.com/ofa-sys/ofa"},{"title":"JHKim-snu/GVCCI","url":"https://github.com/JHKim-snu/GVCCI"},{"title":"JHKim-snu/PGA","url":"https://github.com/JHKim-snu/PGA"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/visual-entailment-on-e-snli-ve","slug":"visual-entailment-on-e-snli-ve","dataset":"e-SNLI-VE","dataset_url":"/dataset/e-snli-ve","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"OFA-X","paper_title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","paper_url":"/paper/harnessing-the-power-of-multi-task","paper_date":"2022-12-08","arxiv_id":"2212.04231","code_links":[{"title":"ofa-x/ofa-x","url":"https://github.com/ofa-x/ofa-x"}],"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/snli-ve","name":"SNLI-VE","full_name":null,"num_papers_in_archive":117},{"url":"/dataset/vsr","name":"VSR","full_name":"Visual Spatial Reasoning","num_papers_in_archive":69},{"url":"/dataset/e-snli-ve","name":"e-SNLI-VE","full_name":"","num_papers_in_archive":16}],"subtasks":[],"parent_tasks":[{"url":"/task/natural-language-inference","name":"Natural Language Inference"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":33,"tagged_in_all":56,"items":[{"url":"/paper/uniter-learning-universal-image-text-1","title":"UNITER: UNiversal Image-TExt Representation Learning","date":"2019-09-25","arxiv_id":"1909.11740","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/coca-contrastive-captioners-are-image-text","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","date":"2022-05-04","arxiv_id":"2205.01917","repositories_listed":6,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/visual-spatial-reasoning","title":"Visual Spatial Reasoning","date":"2022-04-30","arxiv_id":"2205.00363","repositories_listed":4,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/unifying-architectures-tasks-and-modalities","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","date":"2022-02-07","arxiv_id":"2202.03052","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/distilled-dual-encoder-model-for-vision","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","date":"2021-12-16","arxiv_id":"2112.08723","repositories_listed":4,"syntology":null},{"url":"/paper/how-much-can-clip-benefit-vision-and-language","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","date":"2021-07-13","arxiv_id":"2107.06383","repositories_listed":4,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":9}},{"url":"/paper/do-lvlms-understand-charts-analyzing-and","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","date":"2023-12-15","arxiv_id":"2312.10160","repositories_listed":3,"syntology":null},{"url":"/paper/seeing-out-of-the-box-end-to-end-pre-training","title":"Seeing Out of tHe bOx: End-to-End Pre-training for Vision-Language Representation Learning","date":"2021-04-07","arxiv_id":"2104.03135","repositories_listed":3,"syntology":null},{"url":"/paper/advancing-grounded-multimodal-named-entity","title":"Advancing Grounded Multimodal Named Entity Recognition via LLM-Based Reformulation and Box-Based Segmentation","date":"2024-06-11","arxiv_id":"2406.07268","repositories_listed":2,"syntology":null},{"url":"/paper/llms-as-bridges-reformulating-grounded","title":"LLMs as Bridges: Reformulating Grounded Multimodal Named Entity Recognition","date":"2024-02-15","arxiv_id":"2402.09989","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-adversarial-training-for-vision","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","date":"2020-06-11","arxiv_id":"2006.06195","repositories_listed":2,"syntology":{"n":20,"n_ran":10,"n_unverified":10,"n_pointer_only":6}},{"url":"/paper/defeasible-visual-entailment-benchmark","title":"Defeasible Visual Entailment: Benchmark, Evaluator, and Reward-Driven Optimization","date":"2024-12-19","arxiv_id":"2412.16232","repositories_listed":1,"syntology":null},{"url":"/paper/v-flute-visual-figurative-language","title":"Understanding Figurative Meaning through Explainable Visual Entailment","date":"2024-05-02","arxiv_id":"2405.01474","repositories_listed":1,"syntology":null},{"url":"/paper/mope-parameter-efficient-and-scalable","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","date":"2024-03-14","arxiv_id":"2403.10568","repositories_listed":1,"syntology":null},{"url":"/paper/veglue-testing-visual-entailment-systems-via","title":"VEglue: Testing Visual Entailment Systems via Object-Aligned Joint Erasing","date":"2024-03-05","arxiv_id":"2403.02581","repositories_listed":1,"syntology":null},{"url":"/paper/p-laplacian-adaptation-for-generative-pre","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","date":"2023-12-17","arxiv_id":"2312.10613","repositories_listed":1,"syntology":null},{"url":"/paper/good-questions-help-zero-shot-image-reasoning","title":"Good Questions Help Zero-Shot Image Reasoning","date":"2023-12-04","arxiv_id":"2312.01598","repositories_listed":1,"syntology":null},{"url":"/paper/stop-pre-training-adapt-visual-language","title":"Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages","date":"2023-06-29","arxiv_id":"2306.16774","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/i-spy-a-metaphor-large-language-models-and","title":"I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors","date":"2023-05-24","arxiv_id":"2305.14724","repositories_listed":1,"syntology":null},{"url":"/paper/are-multimodal-models-robust-to-image-and","title":"Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift","date":"2022-12-15","arxiv_id":"2212.08044","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/harnessing-the-power-of-multi-task","title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","date":"2022-12-08","arxiv_id":"2212.04231","repositories_listed":1,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/i-can-t-believe-there-s-no-images-learning","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","date":"2022-11-17","arxiv_id":"2211.09778","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/map-modality-agnostic-uncertainty-aware","title":"MAP: Multimodal Uncertainty-Aware Vision-Language Pre-training Model","date":"2022-10-11","arxiv_id":"2210.05335","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-vision-language-pretraining-with","title":"Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment","date":"2022-08-29","arxiv_id":"2208.13628","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/prompt-tuning-for-generative-multimodal","title":"Prompt Tuning for Generative Multimodal Pretrained Models","date":"2022-08-04","arxiv_id":"2208.02532","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/chunk-aware-alignment-and-lexical-constraint","title":"Chunk-aware Alignment and Lexical Constraint for Visual Entailment with Natural Language Explanations","date":"2022-07-23","arxiv_id":"2207.11401","repositories_listed":1,"syntology":null},{"url":"/paper/mixgen-a-new-multi-modal-data-augmentation","title":"MixGen: A New Multi-Modal Data Augmentation","date":"2022-06-16","arxiv_id":"2206.08358","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fine-grained-visual-entailment","title":"Fine-Grained Visual Entailment","date":"2022-03-29","arxiv_id":"2203.15704","repositories_listed":1,"syntology":null},{"url":"/paper/nlx-gpt-a-model-for-natural-language","title":"NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks","date":"2022-03-09","arxiv_id":"2203.05081","repositories_listed":1,"syntology":null},{"url":"/paper/check-it-again-progressive-visual-question-1","title":"Check It Again:Progressive Visual Question Answering via Visual Entailment","date":"2021-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}