{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/visual-prompting","name":"Visual Prompting","slug":"visual-prompting","description_markdown":"Visual Prompting is the task of streamlining computer vision processes by harnessing the power of prompts,\r\ninspired by the breakthroughs of text prompting in NLP. This innovative approach involves using a few visual\r\nprompts to swiftly convert an unlabeled dataset into a deployed model, significantly reducing development time\r\nfor both individual projects and enterprise solutions.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Music","url":"/area/music"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Robots","url":"/area/robots"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":127,"papers_with_code":60,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":2},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/10-shot-image-generation","name":"10-shot image generation"},{"url":"/task/prompt-engineering","name":"Prompt Engineering"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":127,"of_with_code":60,"tagged_in_all":127,"counts":{"archive_papers_tagged":127,"with_a_code_link":60,"where_syntology_ran_a_sample":26,"not_listed_spam_title":0,"listed":127,"listed_where_code_ran":26,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":7,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/segment-anything","slug":"segment-anything","title":"Segment Anything","date":"2023-04-05","arxiv_id":"2304.02643","repositories_listed":32,"syntology":{"n":23,"n_ran":20,"n_constructed":0,"n_ran_checked":14,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":11,"n_pointer_only":2,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 2 violated, 11 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/segment-anything#ran","syntology_url":"https://syntology.ai/paper/2304.02643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02643"}},"official":{"repos":["facebookresearch/segment-anything"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/making-large-multimodal-models-understand","slug":"making-large-multimodal-models-understand","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","date":"2023-12-01","arxiv_id":"2312.00784","repositories_listed":4,"syntology":null},{"url":"/paper/set-of-mark-prompting-unleashes-extraordinary","slug":"set-of-mark-prompting-unleashes-extraordinary","title":"Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V","date":"2023-10-17","arxiv_id":"2310.11441","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/set-of-mark-prompting-unleashes-extraordinary#ran","syntology_url":"https://syntology.ai/paper/2310.11441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11441"}},"official":{"repos":["microsoft/SoM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/visual-in-context-prompting","slug":"visual-in-context-prompting","title":"Visual In-Context Prompting","date":"2023-11-22","arxiv_id":"2311.13601","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/visual-in-context-prompting#ran","syntology_url":"https://syntology.ai/paper/2311.13601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.13601"}},"official":{"repos":["ux-decoder/dinov"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/reprogramming-under-constraints-revisiting","slug":"reprogramming-under-constraints-revisiting","title":"Uncovering the Hidden Cost of Model Compression","date":"2023-08-29","arxiv_id":"2308.14969","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reprogramming-under-constraints-revisiting#ran","syntology_url":"https://syntology.ai/paper/2308.14969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.14969"}},"official":{"repos":["landskape-ai/reprogram_lt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/explicit-visual-prompting-for-universal","slug":"explicit-visual-prompting-for-universal","title":"Explicit Visual Prompting for Universal Foreground Segmentations","date":"2023-05-29","arxiv_id":"2305.18476","repositories_listed":2,"syntology":null},{"url":"/paper/visual-prompting-for-adversarial-robustness","slug":"visual-prompting-for-adversarial-robustness","title":"Visual Prompting for Adversarial Robustness","date":"2022-10-12","arxiv_id":"2210.06284","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-prompting-for-adversarial-robustness#ran","syntology_url":"https://syntology.ai/paper/2210.06284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06284"}},"official":{"repos":["Phoveran/vp-for-adversarial-robustness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stepwise-decomposition-and-dual-stream-focus","slug":"stepwise-decomposition-and-dual-stream-focus","title":"Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation","date":"2025-06-07","arxiv_id":"2506.06818","repositories_listed":1,"syntology":null},{"url":"/paper/vision-graph-prompting-via-semantic-low-rank","slug":"vision-graph-prompting-via-semantic-low-rank","title":"Vision Graph Prompting via Semantic Low-Rank Decomposition","date":"2025-05-07","arxiv_id":"2505.04121","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vision-graph-prompting-via-semantic-low-rank#ran","syntology_url":"https://syntology.ai/paper/2505.04121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04121"}},"official":{"repos":["zhoujiahuan1991/icml2025-vgp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/token-coordinated-prompt-attention-is-needed","slug":"token-coordinated-prompt-attention-is-needed","title":"Token Coordinated Prompt Attention is Needed for Visual Prompting","date":"2025-05-05","arxiv_id":"2505.02406","repositories_listed":1,"syntology":null},{"url":"/paper/towards-online-multi-modal-social-interaction","slug":"towards-online-multi-modal-social-interaction","title":"Towards Online Multi-Modal Social Interaction Understanding","date":"2025-03-25","arxiv_id":"2503.19851","repositories_listed":1,"syntology":null},{"url":"/paper/chameleon-fast-slow-neuro-symbolic-lane","slug":"chameleon-fast-slow-neuro-symbolic-lane","title":"Chameleon: Fast-slow Neuro-symbolic Lane Topology Extraction","date":"2025-03-10","arxiv_id":"2503.07485","repositories_listed":1,"syntology":null},{"url":"/paper/towards-ambiguity-free-spatial-foundation","slug":"towards-ambiguity-free-spatial-foundation","title":"Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity","date":"2025-03-08","arxiv_id":"2503.06014","repositories_listed":1,"syntology":null},{"url":"/paper/lor-vp-low-rank-visual-prompting-for","slug":"lor-vp-low-rank-visual-prompting-for","title":"LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation","date":"2025-02-02","arxiv_id":"2502.00896","repositories_listed":1,"syntology":null},{"url":"/paper/bringing-characters-to-new-stories-training","slug":"bringing-characters-to-new-stories-training","title":"IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting","date":"2025-01-26","arxiv_id":"2501.15641","repositories_listed":1,"syntology":null},{"url":"/paper/gpt4scene-understand-3d-scenes-from-videos","slug":"gpt4scene-understand-3d-scenes-from-videos","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","date":"2025-01-02","arxiv_id":"2501.01428","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gpt4scene-understand-3d-scenes-from-videos#ran","syntology_url":"https://syntology.ai/paper/2501.01428","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.01428"}},"official":{"repos":["Qi-Zhangyang/GPT4Scene"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-visual-prompting-in-vision-mamba","slug":"selective-visual-prompting-in-vision-mamba","title":"Selective Visual Prompting in Vision Mamba","date":"2024-12-12","arxiv_id":"2412.08947","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selective-visual-prompting-in-vision-mamba#ran","syntology_url":"https://syntology.ai/paper/2412.08947","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08947"}},"official":{"repos":["zhoujiahuan1991/aaai2025-svp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/inst-it-boosting-multimodal-instance","slug":"inst-it-boosting-multimodal-instance","title":"Inst-IT: Boosting Multimodal Instance Understanding via Explicit Visual Prompt Instruction Tuning","date":"2024-12-04","arxiv_id":"2412.03565","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inst-it-boosting-multimodal-instance#ran","syntology_url":"https://syntology.ai/paper/2412.03565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03565"}},"official":{"repos":["inst-it/inst-it"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/improved-gui-grounding-via-iterative","slug":"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/benchmarking-human-and-automated-prompting-in","slug":"benchmarking-human-and-automated-prompting-in","title":"Benchmarking Human and Automated Prompting in the Segment Anything Model","date":"2024-10-29","arxiv_id":"2410.22048","repositories_listed":1,"syntology":null},{"url":"/paper/improving-visual-object-tracking-through","slug":"improving-visual-object-tracking-through","title":"Improving Visual Object Tracking through Visual Prompting","date":"2024-09-27","arxiv_id":"2409.18901","repositories_listed":1,"syntology":null},{"url":"/paper/attention-prompting-on-image-for-large-vision","slug":"attention-prompting-on-image-for-large-vision","title":"Attention Prompting on Image for Large Vision-Language Models","date":"2024-09-25","arxiv_id":"2409.17143","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":3,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/attention-prompting-on-image-for-large-vision#ran","syntology_url":"https://syntology.ai/paper/2409.17143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17143"}},"official":{"repos":["yu-rp/apiprompting"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/when-does-visual-prompting-outperform-linear","slug":"when-does-visual-prompting-outperform-linear","title":"When Does Visual Prompting Outperform Linear Probing for Vision-Language Models? A Likelihood Perspective","date":"2024-09-03","arxiv_id":"2409.01821","repositories_listed":1,"syntology":null},{"url":"/paper/open-vocabulary-temporal-action-localization-1","slug":"open-vocabulary-temporal-action-localization-1","title":"Open-Vocabulary Action Localization with Iterative Visual Prompting","date":"2024-08-30","arxiv_id":"2408.17422","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-vocabulary-temporal-action-localization-1#ran","syntology_url":"https://syntology.ai/paper/2408.17422","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.17422"}},"official":null}},{"url":"/paper/2408-03043","slug":"2408-03043","title":"Targeted Visual Prompting for Medical Visual Question Answering","date":"2024-08-06","arxiv_id":"2408.03043","repositories_listed":1,"syntology":null},{"url":"/paper/earthmarker-a-visual-prompt-learning","slug":"earthmarker-a-visual-prompt-learning","title":"EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing","date":"2024-07-18","arxiv_id":"2407.13596","repositories_listed":1,"syntology":null},{"url":"/paper/by-my-eyes-grounding-multimodal-large","slug":"by-my-eyes-grounding-multimodal-large","title":"By My Eyes: Grounding Multimodal Large Language Models with Sensor Data via Visual Prompting","date":"2024-07-15","arxiv_id":"2407.10385","repositories_listed":1,"syntology":null},{"url":"/paper/uicrit-enhancing-automated-design-evaluation","slug":"uicrit-enhancing-automated-design-evaluation","title":"UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset","date":"2024-07-11","arxiv_id":"2407.08850","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-domains-dynamic-solutions-dpcore-for","slug":"dynamic-domains-dynamic-solutions-dpcore-for","title":"Dynamic Domains, Dynamic Solutions: DPCore for Continual Test-Time Adaptation","date":"2024-06-15","arxiv_id":"2406.10737","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dynamic-domains-dynamic-solutions-dpcore-for#ran","syntology_url":"https://syntology.ai/paper/2406.10737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10737"}},"official":{"repos":["zybeich/DPCore"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ot-vp-optimal-transport-guided-visual","slug":"ot-vp-optimal-transport-guided-visual","title":"OT-VP: Optimal Transport-guided Visual Prompting for Test-Time Adaptation","date":"2024-06-12","arxiv_id":"2407.09498","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":4,"n_honours":4,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ot-vp-optimal-transport-guided-visual#ran","syntology_url":"https://syntology.ai/paper/2407.09498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09498"}},"official":{"repos":["zybeich/ot-vp"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-text-cross-alignment-refining-the","slug":"visual-text-cross-alignment-refining-the","title":"Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models","date":"2024-06-05","arxiv_id":"2406.02915","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":0,"n_instrument":8,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visual-text-cross-alignment-refining-the#ran","syntology_url":"https://syntology.ai/paper/2406.02915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02915"}},"official":{"repos":["tmlr-group/wca"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/memory-space-visual-prompting-for-efficient","slug":"memory-space-visual-prompting-for-efficient","title":"Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning","date":"2024-05-09","arxiv_id":"2405.05615","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":5,"n_instrument":9,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":1,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/memory-space-visual-prompting-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2405.05615","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05615"}},"official":{"repos":["jieshibo/memvp"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/groma-localized-visual-tokenization-for","slug":"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":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":2,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/groma-localized-visual-tokenization-for#ran","syntology_url":"https://syntology.ai/paper/2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"official":{"repos":["FoundationVision/Groma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/exploring-the-transferability-of-visual","slug":"exploring-the-transferability-of-visual","title":"Exploring the Transferability of Visual Prompting for Multimodal Large Language Models","date":"2024-04-17","arxiv_id":"2404.11207","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/exploring-the-transferability-of-visual#ran","syntology_url":"https://syntology.ai/paper/2404.11207","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.11207"}},"official":{"repos":["zycheiheihei/transferable-visual-prompting"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/visual-prompting-for-generalized-few-shot","slug":"visual-prompting-for-generalized-few-shot","title":"Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach","date":"2024-04-17","arxiv_id":"2404.11732","repositories_listed":1,"syntology":null},{"url":"/paper/finding-visual-task-vectors","slug":"finding-visual-task-vectors","title":"Finding Visual Task Vectors","date":"2024-04-08","arxiv_id":"2404.05729","repositories_listed":1,"syntology":{"n":11,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":11,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/finding-visual-task-vectors#ran","syntology_url":"https://syntology.ai/paper/2404.05729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05729"}},"official":{"repos":["alhojel/visual_task_vectors"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/draw-and-understand-leveraging-visual-prompts","slug":"draw-and-understand-leveraging-visual-prompts","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","date":"2024-03-29","arxiv_id":"2403.20271","repositories_listed":1,"syntology":null},{"url":"/paper/scaffolding-coordinates-to-promote-vision","slug":"scaffolding-coordinates-to-promote-vision","title":"Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models","date":"2024-02-19","arxiv_id":"2402.12058","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/scaffolding-coordinates-to-promote-vision#ran","syntology_url":"https://syntology.ai/paper/2402.12058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12058"}},"official":{"repos":["leixy20/scaffold"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/tune-an-ellipse-clip-has-potential-to-find","slug":"tune-an-ellipse-clip-has-potential-to-find","title":"Tune-An-Ellipse: CLIP Has Potential to Find What You Want","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generative-multimodal-models-are-in-context","slug":"generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","date":"2023-12-20","arxiv_id":"2312.13286","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/generative-multimodal-models-are-in-context#ran","syntology_url":"https://syntology.ai/paper/2312.13286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13286"}},"official":{"repos":["baaivision/emu"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenize-anything-via-prompting","slug":"tokenize-anything-via-prompting","title":"Tokenize Anything via Prompting","date":"2023-12-14","arxiv_id":"2312.09128","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tokenize-anything-via-prompting#ran","syntology_url":"https://syntology.ai/paper/2312.09128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09128"}},"official":{"repos":["baaivision/tokenize-anything"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ez-clip-efficient-zeroshot-video-action","slug":"ez-clip-efficient-zeroshot-video-action","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","date":"2023-12-13","arxiv_id":"2312.08010","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":0,"n_instrument":9,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ez-clip-efficient-zeroshot-video-action#ran","syntology_url":"https://syntology.ai/paper/2312.08010","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08010"}},"official":{"repos":["shahzadnit/ez-clip"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/visconet-bridging-and-harmonizing-visual-and","slug":"visconet-bridging-and-harmonizing-visual-and","title":"ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet","date":"2023-12-05","arxiv_id":"2312.03154","repositories_listed":1,"syntology":null},{"url":"/paper/visual-prompting-upgrades-neural-network","slug":"visual-prompting-upgrades-neural-network","title":"Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective","date":"2023-12-03","arxiv_id":"2312.01397","repositories_listed":1,"syntology":null},{"url":"/paper/geosam-fine-tuning-sam-with-sparse-and-dense","slug":"geosam-fine-tuning-sam-with-sparse-and-dense","title":"GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation","date":"2023-11-19","arxiv_id":"2311.11319","repositories_listed":1,"syntology":null},{"url":"/paper/autovp-an-automated-visual-prompting","slug":"autovp-an-automated-visual-prompting","title":"AutoVP: An Automated Visual Prompting Framework and Benchmark","date":"2023-10-12","arxiv_id":"2310.08381","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/autovp-an-automated-visual-prompting#ran","syntology_url":"https://syntology.ai/paper/2310.08381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.08381"}},"official":{"repos":["IBM/AutoVP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-instruction-inversion-image-editing","slug":"visual-instruction-inversion-image-editing","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","date":"2023-07-26","arxiv_id":"2307.14331","repositories_listed":1,"syntology":null},{"url":"/paper/fast-segment-anything","slug":"fast-segment-anything","title":"Fast Segment Anything","date":"2023-06-21","arxiv_id":"2306.12156","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-visual-prompting","slug":"fine-grained-visual-prompting","title":"Fine-Grained Visual Prompting","date":"2023-06-07","arxiv_id":"2306.04356","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-pre-trained-language-models-to","slug":"adapting-pre-trained-language-models-to","title":"Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting","date":"2023-06-01","arxiv_id":"2306.00409","repositories_listed":1,"syntology":null},{"url":"/paper/upgpt-universal-diffusion-model-for-person","slug":"upgpt-universal-diffusion-model-for-person","title":"UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer","date":"2023-04-18","arxiv_id":"2304.08870","repositories_listed":1,"syntology":null},{"url":"/paper/blackvip-black-box-visual-prompting-for","slug":"blackvip-black-box-visual-prompting-for","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","date":"2023-03-26","arxiv_id":"2303.14773","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-benefits-of-visual-prompting-in","slug":"exploring-the-benefits-of-visual-prompting-in","title":"Exploring the Benefits of Visual Prompting in Differential Privacy","date":"2023-03-22","arxiv_id":"2303.12247","repositories_listed":1,"syntology":null},{"url":"/paper/explicit-visual-prompting-for-low-level","slug":"explicit-visual-prompting-for-low-level","title":"Explicit Visual Prompting for Low-Level Structure Segmentations","date":"2023-03-20","arxiv_id":"2303.10883","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":3,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explicit-visual-prompting-for-low-level#ran","syntology_url":"https://syntology.ai/paper/2303.10883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.10883"}},"official":{"repos":["nifangbaage/explicit-visual-prompt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diversity-aware-meta-visual-prompting","slug":"diversity-aware-meta-visual-prompting","title":"Diversity-Aware Meta Visual Prompting","date":"2023-03-14","arxiv_id":"2303.08138","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diversity-aware-meta-visual-prompting#ran","syntology_url":"https://syntology.ai/paper/2303.08138","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08138"}},"official":{"repos":["shikiw/dam-vp"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/text-visual-prompting-for-efficient-2d","slug":"text-visual-prompting-for-efficient-2d","title":"Text-Visual Prompting for Efficient 2D Temporal Video Grounding","date":"2023-03-09","arxiv_id":"2303.04995","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/text-visual-prompting-for-efficient-2d#ran","syntology_url":"https://syntology.ai/paper/2303.04995","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04995"}},"official":{"repos":["intel/TVP"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/unleashing-the-power-of-visual-prompting-at","slug":"unleashing-the-power-of-visual-prompting-at","title":"Unleashing the Power of Visual Prompting At the Pixel Level","date":"2022-12-20","arxiv_id":"2212.10556","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unleashing-the-power-of-visual-prompting-at#ran","syntology_url":"https://syntology.ai/paper/2212.10556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.10556"}},"official":{"repos":["ucsc-vlaa/evp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-and-improving-visual-prompting","slug":"understanding-and-improving-visual-prompting","title":"Understanding and Improving Visual Prompting: A Label-Mapping Perspective","date":"2022-11-21","arxiv_id":"2211.11635","repositories_listed":1,"syntology":null},{"url":"/paper/visual-prompting-via-image-inpainting","slug":"visual-prompting-via-image-inpainting","title":"Visual Prompting via Image Inpainting","date":"2022-09-01","arxiv_id":"2209.00647","repositories_listed":1,"syntology":null},{"url":"/paper/visual-prompting-modifying-pixel-space-to","slug":"visual-prompting-modifying-pixel-space-to","title":"Exploring Visual Prompts for Adapting Large-Scale Models","date":"2022-03-31","arxiv_id":"2203.17274","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-prompting-modifying-pixel-space-to#ran","syntology_url":"https://syntology.ai/paper/2203.17274","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.17274"}},"official":{"repos":["hjbahng/visual_prompting"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"rsvp-reasoning-segmentation-via-visual","title":"RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-Thought","date":"2025-06-04","arxiv_id":"2506.04277","repositories_listed":0,"syntology":null},{"url":null,"slug":"grid-logat-grid-based-local-and-global-area","title":"Grid-LOGAT: Grid Based Local and Global Area Transcription for Video Question Answering","date":"2025-05-30","arxiv_id":"2505.24371","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-evaluation-of-multi-modal","title":"A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis","date":"2025-05-29","arxiv_id":"2505.23601","repositories_listed":0,"syntology":null},{"url":null,"slug":"dino-r1-incentivizing-reasoning-capability-in","title":"DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models","date":"2025-05-29","arxiv_id":"2505.24025","repositories_listed":0,"syntology":null},{"url":null,"slug":"vp-lab-a-peft-enabled-visual-prompting","title":"VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation","date":"2025-05-21","arxiv_id":"2505.15592","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-box-visual-prompt-engineering-for","title":"Black-Box Visual Prompt Engineering for Mitigating Object Hallucination in Large Vision Language Models","date":"2025-04-30","arxiv_id":"2504.21559","repositories_listed":0,"syntology":null},{"url":null,"slug":"zoomer-adaptive-image-focus-optimization-for","title":"Zoomer: Adaptive Image Focus Optimization for Black-box MLLM","date":"2025-04-30","arxiv_id":"2505.00742","repositories_listed":0,"syntology":null},{"url":null,"slug":"radsam-segmenting-3d-radiological-images-with","title":"RadSAM: Segmenting 3D radiological images with a 2D promptable model","date":"2025-04-29","arxiv_id":"2504.20837","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-and-textual-prompts-for-enhancing","title":"Visual and textual prompts for enhancing emotion recognition in video","date":"2025-04-24","arxiv_id":"2504.17224","repositories_listed":0,"syntology":null},{"url":null,"slug":"nvsmask3d-hard-visual-prompting-with-camera","title":"NVSMask3D: Hard Visual Prompting with Camera Pose Interpolation for 3D Open Vocabulary Instance Segmentation","date":"2025-04-20","arxiv_id":"2504.14638","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-prompting-for-one-shot-controllable","title":"Visual Prompting for One-shot Controllable Video Editing without Inversion","date":"2025-04-19","arxiv_id":"2504.14335","repositories_listed":0,"syntology":null},{"url":null,"slug":"earthgpt-x-enabling-mllms-to-flexibly-and","title":"EarthGPT-X: Enabling MLLMs to Flexibly and Comprehensively Understand Multi-Source Remote Sensing Imagery","date":"2025-04-17","arxiv_id":"2504.12795","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-temporal-prompting-all-we-need-for-limited","title":"Is Temporal Prompting All We Need For Limited Labeled Action Recognition?","date":"2025-04-02","arxiv_id":"2504.01890","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-guided-attention-head-selection-for","title":"Prompt-Guided Attention Head Selection for Focus-Oriented Image Retrieval","date":"2025-04-02","arxiv_id":"2504.01348","repositories_listed":0,"syntology":null},{"url":null,"slug":"vp-ntk-exploring-the-benefits-of-visual","title":"VP-NTK: Exploring the Benefits of Visual Prompting in Differentially Private Data Synthesis","date":"2025-03-20","arxiv_id":"2503.16195","repositories_listed":0,"syntology":null},{"url":null,"slug":"3daxisprompt-promoting-the-3d-grounding-and","title":"3DAxisPrompt: Promoting the 3D Grounding and Reasoning in GPT-4o","date":"2025-03-17","arxiv_id":"2503.13185","repositories_listed":0,"syntology":null},{"url":null,"slug":"kuda-keypoints-to-unify-dynamics-learning-and","title":"KUDA: Keypoints to Unify Dynamics Learning and Visual Prompting for Open-Vocabulary Robotic Manipulation","date":"2025-03-13","arxiv_id":"2503.10546","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-universal-text-driven-ct-image","title":"Towards Universal Text-driven CT Image Segmentation","date":"2025-03-08","arxiv_id":"2503.06030","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-role-of-background-information-in","title":"The Role of Background Information in Reducing Object Hallucination in Vision-Language Models: Insights from Cutoff API Prompting","date":"2025-02-21","arxiv_id":"2502.15389","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-powerpoint-ui-sketches-to-web-based","title":"From PowerPoint UI Sketches to Web-Based Applications: Pattern-Driven Code Generation for GIS Dashboard Development Using Knowledge-Augmented LLMs, Context-Aware Visual Prompting, and the React Framework","date":"2025-02-12","arxiv_id":"2502.08756","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulate-anymesh-open-vocabulary-3d","title":"Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling","date":"2025-02-04","arxiv_id":"2502.02590","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalization-toolkit-training-free","title":"Personalization Toolkit: Training Free Personalization of Large Vision Language Models","date":"2025-02-04","arxiv_id":"2502.02452","repositories_listed":0,"syntology":null},{"url":null,"slug":"medfocusclip-improving-few-shot","title":"MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention","date":"2025-01-07","arxiv_id":"2501.03839","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-efficient-black-box-visual-prompting","title":"Query Efficient Black-Box Visual Prompting with Subspace Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-prompting-with-iterative-refinement","title":"Visual Prompting with Iterative Refinement for Design Critique Generation","date":"2024-12-22","arxiv_id":"2412.16829","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-correction-with-human-feedback-an","title":"Test-time Correction with Human Feedback: An Online 3D Detection System via Visual Prompting","date":"2024-12-10","arxiv_id":"2412.07768","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-search-a-zero-shot-approach-to-finding","title":"MLLM-Search: A Zero-Shot Approach to Finding People using Multimodal Large Language Models","date":"2024-11-27","arxiv_id":"2412.00103","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-the-unseen-detecting-hidden","title":"Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models","date":"2024-11-14","arxiv_id":"2411.09540","repositories_listed":0,"syntology":null},{"url":null,"slug":"weathergfm-learning-a-weather-generalist","title":"WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning","date":"2024-11-08","arxiv_id":"2411.05420","repositories_listed":0,"syntology":null},{"url":null,"slug":"ferret-ui-2-mastering-universal-user","title":"Ferret-UI 2: Mastering Universal User Interface Understanding Across Platforms","date":"2024-10-24","arxiv_id":"2410.18967","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-prompting-in-llms-for-enhancing","title":"Visual Prompting in LLMs for Enhancing Emotion Recognition","date":"2024-10-03","arxiv_id":"2410.02244","repositories_listed":0,"syntology":null},{"url":null,"slug":"gson-a-group-based-social-navigation","title":"GSON: A Group-based Social Navigation Framework with Large Multimodal Model","date":"2024-09-26","arxiv_id":"2409.18084","repositories_listed":0,"syntology":null},{"url":null,"slug":"cycle-consistency-uncertainty-estimation-for","title":"Cycle-Consistency Uncertainty Estimation for Visual Prompting based One-Shot Defect Segmentation","date":"2024-09-21","arxiv_id":"2409.13984","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-open-vocabulary-video-visual","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","date":"2024-09-19","arxiv_id":"2409.12499","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-prompting-in-multimodal-large-language","title":"Visual Prompting in Multimodal Large Language Models: A Survey","date":"2024-09-05","arxiv_id":"2409.15310","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-sparse-lexical-representations-for","title":"Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Models","date":"2024-08-29","arxiv_id":"2408.16296","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00754","title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","date":"2024-08-01","arxiv_id":"2408.00754","repositories_listed":0,"syntology":null},{"url":null,"slug":"chat2layout-interactive-3d-furniture-layout","title":"Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM","date":"2024-07-31","arxiv_id":"2407.21333","repositories_listed":0,"syntology":null},{"url":null,"slug":"affordance-guided-reinforcement-learning-via","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","date":"2024-07-14","arxiv_id":"2407.10341","repositories_listed":0,"syntology":null},{"url":null,"slug":"degustabot-zero-shot-visual-preference","title":"DegustaBot: Zero-Shot Visual Preference Estimation for Personalized Multi-Object Rearrangement","date":"2024-07-11","arxiv_id":"2407.08876","repositories_listed":0,"syntology":null}],"syntology_records":28,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":26,"papers_where_code_ran_first_page":"/task/visual-prompting/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/visual-prompting/papers/2","json":"/task/visual-prompting/papers/2.json","rows":27},{"order":"ran","page":1,"of":1,"url":"/task/visual-prompting/papers/ran/1","json":"/task/visual-prompting/papers/ran/1.json","rows":26}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"5b23f85d208b7a5293a8641347a7d19104fa86001032af84e24c6e3ccb75b7f6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}