{"url":"/task/natural-language-visual-grounding","name":"Natural Language Visual Grounding","slug":"natural-language-visual-grounding","description_markdown":null,"categories":[{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":32,"papers_with_code":30,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":7,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/natural-language-visual-grounding-on","slug":"natural-language-visual-grounding-on","dataset":"ScreenSpot","dataset_url":"/dataset/screenspot","rows_in_archive":18,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"UGround-V1-7B","paper_title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","paper_url":"/paper/navigating-the-digital-world-as-humans-do","paper_date":"2024-10-07","arxiv_id":"2410.05243","code_links":[{"title":"OSU-NLP-Group/UGround","url":"https://github.com/OSU-NLP-Group/UGround"}],"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/referit3d","name":"ReferIt3D","full_name":"","num_papers_in_archive":104},{"url":"/dataset/screenspot","name":"ScreenSpot","full_name":"","num_papers_in_archive":47},{"url":"/dataset/google-refexp","name":"Google Refexp","full_name":"","num_papers_in_archive":46},{"url":"/dataset/mad","name":"MAD","full_name":"","num_papers_in_archive":36},{"url":"/dataset/spot-the-diff","name":"Spot-the-diff","full_name":"","num_papers_in_archive":35},{"url":"/dataset/imagecode","name":"ImageCoDe","full_name":"Image Retrieval from Contextual Descriptions","num_papers_in_archive":11},{"url":"/dataset/metu-viref-dataset","name":"METU-VIREF Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":30,"tagged_in_all":32,"items":[{"url":"/paper/alfred-a-benchmark-for-interpreting-grounded","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","date":"2019-12-03","arxiv_id":"1912.01734","repositories_listed":11,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/qwen2-vl-enhancing-vision-language-model-s","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","date":"2024-09-18","arxiv_id":"2409.12191","repositories_listed":8,"syntology":{"n":12,"n_ran":8,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/cogagent-a-visual-language-model-for-gui","title":"CogAgent: A Visual Language Model for GUI Agents","date":"2023-12-14","arxiv_id":"2312.08914","repositories_listed":3,"syntology":{"n":18,"n_ran":12,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/grounding-of-textual-phrases-in-images-by","title":"Grounding of Textual Phrases in Images by Reconstruction","date":"2015-11-12","arxiv_id":"1511.03745","repositories_listed":3,"syntology":null},{"url":"/paper/os-atlas-a-foundation-action-model-for","title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","date":"2024-10-30","arxiv_id":"2410.23218","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/minigpt-v2-large-language-model-as-a-unified","title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","date":"2023-10-14","arxiv_id":"2310.09478","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","date":"2023-08-24","arxiv_id":"2308.12966","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/composing-pick-and-place-tasks-by-grounding","title":"Composing Pick-and-Place Tasks By Grounding Language","date":"2021-02-16","arxiv_id":"2102.08094","repositories_listed":2,"syntology":null},{"url":"/paper/alfworld-aligning-text-and-embodied","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","date":"2020-10-08","arxiv_id":"2010.03768","repositories_listed":2,"syntology":{"n":14,"n_ran":11,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/self-monitoring-navigation-agent-via","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","date":"2019-01-10","arxiv_id":"1901.03035","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/aria-ui-visual-grounding-for-gui-instructions","title":"Aria-UI: Visual Grounding for GUI Instructions","date":"2024-12-20","arxiv_id":"2412.16256","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/aguvis-unified-pure-vision-agents-for","title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","date":"2024-12-05","arxiv_id":"2412.04454","repositories_listed":1,"syntology":null},{"url":"/paper/showui-one-vision-language-action-model-for","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","date":"2024-11-26","arxiv_id":"2411.17465","repositories_listed":1,"syntology":{"n":16,"n_ran":1,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/improved-gui-grounding-via-iterative","title":"Improved GUI Grounding via Iterative Narrowing","date":"2024-11-18","arxiv_id":"2411.13591","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-the-digital-world-as-humans-do","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","date":"2024-10-07","arxiv_id":"2410.05243","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/omniparser-for-pure-vision-based-gui-agent","title":"OmniParser for Pure Vision Based GUI Agent","date":"2024-08-01","arxiv_id":"2408.00203","repositories_listed":1,"syntology":null},{"url":"/paper/guicourse-from-general-vision-language-models","title":"GUICourse: From General Vision Language Models to Versatile GUI Agents","date":"2024-06-17","arxiv_id":"2406.11317","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_unverified":1,"n_pointer_only":16}},{"url":"/paper/groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","date":"2024-04-19","arxiv_id":"2404.13013","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/seeclick-harnessing-gui-grounding-for","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","date":"2024-01-17","arxiv_id":"2401.10935","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/localizing-moments-in-long-video-via","title":"Localizing Moments in Long Video Via Multimodal Guidance","date":"2023-02-26","arxiv_id":"2302.13372","repositories_listed":1,"syntology":null},{"url":"/paper/belief-revision-based-caption-re-ranker-with","title":"Belief Revision based Caption Re-ranker with Visual Semantic Information","date":"2022-09-16","arxiv_id":"2209.08163","repositories_listed":1,"syntology":null},{"url":"/paper/tubedetr-spatio-temporal-video-grounding-with","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","date":"2022-03-30","arxiv_id":"2203.16434","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/calvin-a-benchmark-for-language-conditioned","title":"CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks","date":"2021-12-06","arxiv_id":"2112.03227","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/panoptic-narrative-grounding","title":"Panoptic Narrative Grounding","date":"2021-09-10","arxiv_id":"2109.04988","repositories_listed":1,"syntology":null},{"url":"/paper/panoptic-narrative-grounding-1","title":"Panoptic Narrative Grounding","date":"2021-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-linguistic-analysis-of-visually-grounded","title":"A Linguistic Analysis of Visually Grounded Dialogues Based on Spatial Expressions","date":"2020-10-07","arxiv_id":"2010.03127","repositories_listed":1,"syntology":null},{"url":"/paper/learning-cross-modal-context-graph-for-visual","title":"Learning Cross-modal Context Graph for Visual Grounding","date":"2020-02-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/searching-for-ambiguous-objects-in-videos","title":"Searching for Ambiguous Objects in Videos using Relational Referring Expressions","date":"2019-08-03","arxiv_id":"1908.01189","repositories_listed":1,"syntology":null},{"url":"/paper/modularized-textual-grounding-for","title":"Modularized Textual Grounding for Counterfactual Resilience","date":"2019-04-07","arxiv_id":"1904.03589","repositories_listed":1,"syntology":null},{"url":"/paper/viewpoint-invariant-change-captioning","title":"Robust Change Captioning","date":"2019-01-08","arxiv_id":"1901.02527","repositories_listed":1,"syntology":null}],"syntology_records":16,"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"}}