{"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-question-answering-1/papers/2","list_of":"/task/visual-question-answering-1","task":"Visual Question Answering","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":22,"rows_per_page":100,"rows":[101,200],"of":2177,"counts":{"archive_papers_tagged":2177,"with_a_code_link":1042,"where_syntology_ran_a_sample":378,"not_listed_spam_title":0,"listed":2177,"listed_where_code_ran":378,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":308,"every_run_a_failure_of_syntologys_instrument":70,"listed_with_a_run_with_no_instrument_failure":308,"listed_every_run_a_failure_of_syntologys_instrument":70,"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"},"first_page":"/task/visual-question-answering-1","prev":"/task/visual-question-answering-1","next":"/task/visual-question-answering-1/papers/3","papers":[{"url":"/paper/2408-02657","slug":"2408-02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","date":"2024-08-05","arxiv_id":"2408.02657","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-02657#ran","syntology_url":"https://syntology.ai/paper/2408.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02657"}},"official":{"repos":["alpha-vllm/lumina-mgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/mm-instruct-generated-visual-instructions-for","slug":"mm-instruct-generated-visual-instructions-for","title":"MM-Instruct: Generated Visual Instructions for Large Multimodal Model Alignment","date":"2024-06-28","arxiv_id":"2406.19736","repositories_listed":2,"syntology":null},{"url":"/paper/learnable-in-context-vector-for-visual","slug":"learnable-in-context-vector-for-visual","title":"LIVE: Learnable In-Context Vector for Visual Question Answering","date":"2024-06-19","arxiv_id":"2406.13185","repositories_listed":2,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/learnable-in-context-vector-for-visual#ran","syntology_url":"https://syntology.ai/paper/2406.13185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13185"}},"official":{"repos":["forjadeforest/live-learnable-in-context-vector"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vane-bench-video-anomaly-evaluation-benchmark","slug":"vane-bench-video-anomaly-evaluation-benchmark","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","date":"2024-06-14","arxiv_id":"2406.10326","repositories_listed":2,"syntology":null},{"url":"/paper/wings-learning-multimodal-llms-without-text","slug":"wings-learning-multimodal-llms-without-text","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","date":"2024-06-05","arxiv_id":"2406.03496","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wings-learning-multimodal-llms-without-text#ran","syntology_url":"https://syntology.ai/paper/2406.03496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03496"}},"official":null}},{"url":"/paper/enhancing-visual-language-modality-alignment","slug":"enhancing-visual-language-modality-alignment","title":"Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement","date":"2024-05-24","arxiv_id":"2405.15973","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/enhancing-visual-language-modality-alignment#ran","syntology_url":"https://syntology.ai/paper/2405.15973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15973"}},"official":{"repos":["umd-huang-lab/sima"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/reframing-spatial-reasoning-evaluation-in","slug":"reframing-spatial-reasoning-evaluation-in","title":"Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning","date":"2024-05-23","arxiv_id":"2405.15064","repositories_listed":2,"syntology":null},{"url":"/paper/viocrvqa-novel-benchmark-dataset-and-vision","slug":"viocrvqa-novel-benchmark-dataset-and-vision","title":"ViOCRVQA: Novel Benchmark Dataset and Vision Reader for Visual Question Answering by Understanding Vietnamese Text in Images","date":"2024-04-29","arxiv_id":"2404.18397","repositories_listed":2,"syntology":null},{"url":"/paper/vitextvqa-a-large-scale-visual-question","slug":"vitextvqa-a-large-scale-visual-question","title":"ViTextVQA: A Large-Scale Visual Question Answering Dataset for Evaluating Vietnamese Text Comprehension in Images","date":"2024-04-16","arxiv_id":"2404.10652","repositories_listed":2,"syntology":null},{"url":"/paper/view-selection-for-3d-captioning-via","slug":"view-selection-for-3d-captioning-via","title":"View Selection for 3D Captioning via Diffusion Ranking","date":"2024-04-11","arxiv_id":"2404.07984","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/view-selection-for-3d-captioning-via#ran","syntology_url":"https://syntology.ai/paper/2404.07984","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07984"}},"official":null}},{"url":"/paper/internlm-xcomposer2-4khd-a-pioneering-large","slug":"internlm-xcomposer2-4khd-a-pioneering-large","title":"InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD","date":"2024-04-09","arxiv_id":"2404.06512","repositories_listed":2,"syntology":null},{"url":"/paper/m3d-advancing-3d-medical-image-analysis-with","slug":"m3d-advancing-3d-medical-image-analysis-with","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","date":"2024-03-31","arxiv_id":"2404.00578","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/m3d-advancing-3d-medical-image-analysis-with#ran","syntology_url":"https://syntology.ai/paper/2404.00578","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00578"}},"official":{"repos":["baai-dcai/m3d"],"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/design-as-desired-utilizing-visual-question","slug":"design-as-desired-utilizing-visual-question","title":"Design as Desired: Utilizing Visual Question Answering for Multimodal Pre-training","date":"2024-03-30","arxiv_id":"2404.00226","repositories_listed":2,"syntology":null},{"url":"/paper/h2rsvlm-towards-helpful-and-honest-remote","slug":"h2rsvlm-towards-helpful-and-honest-remote","title":"VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis","date":"2024-03-29","arxiv_id":"2403.20213","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/h2rsvlm-towards-helpful-and-honest-remote#ran","syntology_url":"https://syntology.ai/paper/2403.20213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.20213"}},"official":{"repos":["opendatalab/h2rsvlm","opendatalab/vhm"],"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"]}}},{"url":"/paper/mini-gemini-mining-the-potential-of-multi","slug":"mini-gemini-mining-the-potential-of-multi","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","date":"2024-03-27","arxiv_id":"2403.18814","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mini-gemini-mining-the-potential-of-multi#ran","syntology_url":"https://syntology.ai/paper/2403.18814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18814"}},"official":{"repos":["dvlab-research/minigemini"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sq-llava-self-questioning-for-large-vision","slug":"sq-llava-self-questioning-for-large-vision","title":"SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant","date":"2024-03-17","arxiv_id":"2403.11299","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sq-llava-self-questioning-for-large-vision#ran","syntology_url":"https://syntology.ai/paper/2403.11299","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11299"}},"official":{"repos":["heliossun/sq-llava"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/are-language-models-puzzle-prodigies","slug":"are-language-models-puzzle-prodigies","title":"Are Language Models Puzzle Prodigies? Algorithmic Puzzles Unveil Serious Challenges in Multimodal Reasoning","date":"2024-03-06","arxiv_id":"2403.03864","repositories_listed":2,"syntology":null},{"url":"/paper/tinyllava-a-framework-of-small-scale-large","slug":"tinyllava-a-framework-of-small-scale-large","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","date":"2024-02-22","arxiv_id":"2402.14289","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"6 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; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/tinyllava-a-framework-of-small-scale-large#ran","syntology_url":"https://syntology.ai/paper/2402.14289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14289"}},"official":{"repos":["dlcv-buaa/tinyllavabench"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-preference-alignment-remedies","slug":"multi-modal-preference-alignment-remedies","title":"Multi-modal Preference Alignment Remedies Degradation of Visual Instruction Tuning on Language Models","date":"2024-02-16","arxiv_id":"2402.10884","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-modal-preference-alignment-remedies#ran","syntology_url":"https://syntology.ai/paper/2402.10884","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10884"}},"official":{"repos":["findalexli/mllm-dpo"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/tinygpt-v-efficient-multimodal-large-language","slug":"tinygpt-v-efficient-multimodal-large-language","title":"TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones","date":"2023-12-28","arxiv_id":"2312.16862","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tinygpt-v-efficient-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2312.16862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16862"}},"official":{"repos":["dlyuangod/tinygpt-v"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/internvl-scaling-up-vision-foundation-models","slug":"internvl-scaling-up-vision-foundation-models","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","date":"2023-12-21","arxiv_id":"2312.14238","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/internvl-scaling-up-vision-foundation-models#ran","syntology_url":"https://syntology.ai/paper/2312.14238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14238"}},"official":{"repos":["opengvlab/internvl"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/lingoqa-video-question-answering-for","slug":"lingoqa-video-question-answering-for","title":"LingoQA: Visual Question Answering for Autonomous Driving","date":"2023-12-21","arxiv_id":"2312.14115","repositories_listed":2,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/lingoqa-video-question-answering-for#ran","syntology_url":"https://syntology.ai/paper/2312.14115","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.14115"}},"official":{"repos":["wayveai/lingoqa"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/advancing-surgical-vqa-with-scene-graph","slug":"advancing-surgical-vqa-with-scene-graph","title":"Advancing Surgical VQA with Scene Graph Knowledge","date":"2023-12-15","arxiv_id":"2312.10251","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/advancing-surgical-vqa-with-scene-graph#ran","syntology_url":"https://syntology.ai/paper/2312.10251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10251"}},"official":{"repos":["camma-public/ssg-qa","camma-public/ssg-vqa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/icd-lm-configuring-vision-language-in-context","slug":"icd-lm-configuring-vision-language-in-context","title":"Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models","date":"2023-12-15","arxiv_id":"2312.10104","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/icd-lm-configuring-vision-language-in-context#ran","syntology_url":"https://syntology.ai/paper/2312.10104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10104"}},"official":{"repos":["forjadeforest/icd-lm","forjadeforest/lever-lm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/benchlmm-benchmarking-cross-style-visual","slug":"benchlmm-benchmarking-cross-style-visual","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","date":"2023-12-05","arxiv_id":"2312.02896","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchlmm-benchmarking-cross-style-visual#ran","syntology_url":"https://syntology.ai/paper/2312.02896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02896"}},"official":{"repos":["aifeg/benchgpt","aifeg/benchlmm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large","slug":"llama-vid-an-image-is-worth-2-tokens-in-large","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","date":"2023-11-28","arxiv_id":"2311.17043","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llama-vid-an-image-is-worth-2-tokens-in-large#ran","syntology_url":"https://syntology.ai/paper/2311.17043","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17043"}},"official":{"repos":["dvlab-research/llama-vid"],"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"]}}},{"url":"/paper/to-see-is-to-believe-prompting-gpt-4v-for","slug":"to-see-is-to-believe-prompting-gpt-4v-for","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","date":"2023-11-13","arxiv_id":"2311.07574","repositories_listed":2,"syntology":null},{"url":"/paper/infmllm-a-unified-framework-for-visual","slug":"infmllm-a-unified-framework-for-visual","title":"InfMLLM: A Unified Framework for Visual-Language Tasks","date":"2023-11-12","arxiv_id":"2311.06791","repositories_listed":2,"syntology":null},{"url":"/paper/mplug-owl2-revolutionizing-multi-modal-large","slug":"mplug-owl2-revolutionizing-multi-modal-large","title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","date":"2023-11-07","arxiv_id":"2311.04257","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/mplug-owl2-revolutionizing-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2311.04257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04257"}},"official":{"repos":["x-plug/mplug-owl"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/3d-aware-visual-question-answering-about-1","slug":"3d-aware-visual-question-answering-about-1","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","date":"2023-10-27","arxiv_id":"2310.17914","repositories_listed":2,"syntology":{"n":28,"n_ran":22,"n_constructed":0,"n_ran_checked":21,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":14,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/3d-aware-visual-question-answering-about-1#ran","syntology_url":"https://syntology.ai/paper/2310.17914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17914"}},"official":{"repos":["xingruiwang/3d-aware-vqa"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lxmert-model-compression-for-visual-question","slug":"lxmert-model-compression-for-visual-question","title":"LXMERT Model Compression for Visual Question Answering","date":"2023-10-23","arxiv_id":"2310.15325","repositories_listed":2,"syntology":null},{"url":"/paper/frozen-transformers-in-language-models-are","slug":"frozen-transformers-in-language-models-are","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","date":"2023-10-19","arxiv_id":"2310.12973","repositories_listed":2,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/frozen-transformers-in-language-models-are#ran","syntology_url":"https://syntology.ai/paper/2310.12973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.12973"}},"official":{"repos":["ziqipang/lm4visualencoding"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/minigpt-v2-large-language-model-as-a-unified","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt-v2-large-language-model-as-a-unified#ran","syntology_url":"https://syntology.ai/paper/2310.09478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09478"}},"official":null}},{"url":"/paper/uncovering-hidden-connections-iterative","slug":"uncovering-hidden-connections-iterative","title":"Uncovering Hidden Connections: Iterative Search and Reasoning for Video-grounded Dialog","date":"2023-10-11","arxiv_id":"2310.07259","repositories_listed":2,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/uncovering-hidden-connections-iterative#ran","syntology_url":"https://syntology.ai/paper/2310.07259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07259"}},"official":{"repos":["hyu-zhang/itr","Hyu-Zhang/ISR"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/qwen-vl-a-frontier-large-vision-language","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/qwen-vl-a-frontier-large-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.12966"}},"official":{"repos":["qwenlm/qwen-vl"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/uni-nlx-unifying-textual-explanations-for","slug":"uni-nlx-unifying-textual-explanations-for","title":"Uni-NLX: Unifying Textual Explanations for Vision and Vision-Language Tasks","date":"2023-08-17","arxiv_id":"2308.09033","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/uni-nlx-unifying-textual-explanations-for#ran","syntology_url":"https://syntology.ai/paper/2308.09033","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09033"}},"official":{"repos":["fawazsammani/uni-nlx","fawazsammani/nlxgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/pro-cap-leveraging-a-frozen-vision-language","slug":"pro-cap-leveraging-a-frozen-vision-language","title":"Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection","date":"2023-08-16","arxiv_id":"2308.08088","repositories_listed":2,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"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) · 3 unverified","sample_list":"/paper/pro-cap-leveraging-a-frozen-vision-language#ran","syntology_url":"https://syntology.ai/paper/2308.08088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08088"}},"official":{"repos":["social-ai-studio/pro-cap"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/openflamingo-an-open-source-framework-for","slug":"openflamingo-an-open-source-framework-for","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","date":"2023-08-02","arxiv_id":"2308.01390","repositories_listed":2,"syntology":null},{"url":"/paper/generative-pretraining-in-multimodality","slug":"generative-pretraining-in-multimodality","title":"Emu: Generative Pretraining in Multimodality","date":"2023-07-11","arxiv_id":"2307.05222","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/generative-pretraining-in-multimodality#ran","syntology_url":"https://syntology.ai/paper/2307.05222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05222"}},"official":{"repos":["baaivision/emu"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/sas-video-qa-self-adaptive-sampling-for","slug":"sas-video-qa-self-adaptive-sampling-for","title":"Self-Adaptive Sampling for Efficient Video Question-Answering on Image--Text Models","date":"2023-07-09","arxiv_id":"2307.04192","repositories_listed":2,"syntology":null},{"url":"/paper/kosmos-2-grounding-multimodal-large-language","slug":"kosmos-2-grounding-multimodal-large-language","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","date":"2023-06-26","arxiv_id":"2306.14824","repositories_listed":2,"syntology":null},{"url":"/paper/mimic-it-multi-modal-in-context-instruction","slug":"mimic-it-multi-modal-in-context-instruction","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","date":"2023-06-08","arxiv_id":"2306.05425","repositories_listed":2,"syntology":null},{"url":"/paper/pmc-vqa-visual-instruction-tuning-for-medical","slug":"pmc-vqa-visual-instruction-tuning-for-medical","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","date":"2023-05-17","arxiv_id":"2305.10415","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pmc-vqa-visual-instruction-tuning-for-medical#ran","syntology_url":"https://syntology.ai/paper/2305.10415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.10415"}},"official":{"repos":["xiaoman-zhang/PMC-VQA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/palm-e-an-embodied-multimodal-language-model","slug":"palm-e-an-embodied-multimodal-language-model","title":"PaLM-E: An Embodied Multimodal Language Model","date":"2023-03-06","arxiv_id":"2303.03378","repositories_listed":2,"syntology":null},{"url":"/paper/can-pre-trained-vision-and-language-models","slug":"can-pre-trained-vision-and-language-models","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","date":"2023-02-23","arxiv_id":"2302.11713","repositories_listed":2,"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":0,"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/can-pre-trained-vision-and-language-models#ran","syntology_url":"https://syntology.ai/paper/2302.11713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.11713"}},"official":{"repos":["edchengg/infoseek_eval"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/super-clevr-a-virtual-benchmark-to-diagnose","slug":"super-clevr-a-virtual-benchmark-to-diagnose","title":"Super-CLEVR: A Virtual Benchmark to Diagnose Domain Robustness in Visual Reasoning","date":"2022-12-01","arxiv_id":"2212.00259","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/super-clevr-a-virtual-benchmark-to-diagnose#ran","syntology_url":"https://syntology.ai/paper/2212.00259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.00259"}},"official":{"repos":["lizw14/super-clevr"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-supervised-vision-language-pretraining","slug":"self-supervised-vision-language-pretraining","title":"Self-supervised vision-language pretraining for Medical visual question answering","date":"2022-11-24","arxiv_id":"2211.13594","repositories_listed":2,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 4 unverified","sample_list":"/paper/self-supervised-vision-language-pretraining#ran","syntology_url":"https://syntology.ai/paper/2211.13594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.13594"}},"official":{"repos":["pengfeiliheu/m2i2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ernie-layout-layout-knowledge-enhanced-pre","slug":"ernie-layout-layout-knowledge-enhanced-pre","title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding","date":"2022-10-12","arxiv_id":"2210.06155","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ernie-layout-layout-knowledge-enhanced-pre#ran","syntology_url":"https://syntology.ai/paper/2210.06155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06155"}},"official":{"repos":["PaddlePaddle/PaddleNLP"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/linearly-mapping-from-image-to-text-space","slug":"linearly-mapping-from-image-to-text-space","title":"Linearly Mapping from Image to Text Space","date":"2022-09-30","arxiv_id":"2209.15162","repositories_listed":2,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/linearly-mapping-from-image-to-text-space#ran","syntology_url":"https://syntology.ai/paper/2209.15162","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.15162"}},"official":{"repos":["jmerullo/limber"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/image-as-a-foreign-language-beit-pretraining","slug":"image-as-a-foreign-language-beit-pretraining","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","date":"2022-08-22","arxiv_id":"2208.10442","repositories_listed":2,"syntology":null},{"url":"/paper/cross-modal-causal-relational-reasoning-for","slug":"cross-modal-causal-relational-reasoning-for","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","date":"2022-07-26","arxiv_id":"2207.12647","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-modal-causal-relational-reasoning-for#ran","syntology_url":"https://syntology.ai/paper/2207.12647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.12647"}},"official":{"repos":["hcplab-sysu/cmcir","yangliu9208/cmcir"],"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/all-you-may-need-for-vqa-are-image-captions-1","slug":"all-you-may-need-for-vqa-are-image-captions-1","title":"All You May Need for VQA are Image Captions","date":"2022-05-04","arxiv_id":"2205.01883","repositories_listed":2,"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/all-you-may-need-for-vqa-are-image-captions-1#ran","syntology_url":"https://syntology.ai/paper/2205.01883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01883"}},"official":{"repos":["google-research-datasets/maverics"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/searching-the-search-space-of-vision-1","slug":"searching-the-search-space-of-vision-1","title":"Searching the Search Space of Vision Transformer","date":"2021-11-29","arxiv_id":"2111.14725","repositories_listed":2,"syntology":null},{"url":"/paper/florence-a-new-foundation-model-for-computer","slug":"florence-a-new-foundation-model-for-computer","title":"Florence: A New Foundation Model for Computer Vision","date":"2021-11-22","arxiv_id":"2111.11432","repositories_listed":2,"syntology":null},{"url":"/paper/vivqa-vietnamese-visual-question-answering","slug":"vivqa-vietnamese-visual-question-answering","title":"ViVQA: Vietnamese Visual Question Answering","date":"2021-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/label-descriptive-patterns-and-their","slug":"label-descriptive-patterns-and-their","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","date":"2021-10-18","arxiv_id":"2110.09599","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 3 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) · 2 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/label-descriptive-patterns-and-their#ran","syntology_url":"https://syntology.ai/paper/2110.09599","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.09599"}},"official":{"repos":["uds-lsv/premise"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/coarse-to-fine-reasoning-for-visual-question","slug":"coarse-to-fine-reasoning-for-visual-question","title":"Coarse-to-Fine Reasoning for Visual Question Answering","date":"2021-10-06","arxiv_id":"2110.02526","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/coarse-to-fine-reasoning-for-visual-question#ran","syntology_url":"https://syntology.ai/paper/2110.02526","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02526"}},"official":{"repos":["aioz-ai/cfr_vqa","aioz-ai/crf_vqa"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/weakly-supervised-visual-retriever-reader-for","slug":"weakly-supervised-visual-retriever-reader-for","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","date":"2021-09-09","arxiv_id":"2109.04014","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/weakly-supervised-visual-retriever-reader-for#ran","syntology_url":"https://syntology.ai/paper/2109.04014","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04014"}},"official":{"repos":["luomancs/retriever_reader_for_okvqa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/simvlm-simple-visual-language-model","slug":"simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","date":"2021-08-24","arxiv_id":"2108.10904","repositories_listed":2,"syntology":{"n":37,"n_ran":22,"n_constructed":8,"n_ran_checked":16,"n_instrument":6,"n_unverified":15,"n_honours":1,"n_violates":3,"n_no_contract":12,"n_pointer_only":32,"phrase":"22 ran (of which 8 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 3 violated, 12 with no contract checked; 6 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/simvlm-simple-visual-language-model#ran","syntology_url":"https://syntology.ai/paper/2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"official":null}},{"url":"/paper/x-modaler-a-versatile-and-high-performance","slug":"x-modaler-a-versatile-and-high-performance","title":"X-modaler: A Versatile and High-performance Codebase for Cross-modal Analytics","date":"2021-08-18","arxiv_id":"2108.08217","repositories_listed":2,"syntology":null},{"url":"/paper/separating-skills-and-concepts-for-novel-1","slug":"separating-skills-and-concepts-for-novel-1","title":"Separating Skills and Concepts for Novel Visual Question Answering","date":"2021-07-19","arxiv_id":"2107.09106","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/separating-skills-and-concepts-for-novel-1#ran","syntology_url":"https://syntology.ai/paper/2107.09106","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.09106"}},"official":{"repos":["SpencerWhitehead/novelvqa"],"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"]}}},{"url":"/paper/zero-shot-visual-question-answering-using","slug":"zero-shot-visual-question-answering-using","title":"Zero-shot Visual Question Answering using Knowledge Graph","date":"2021-07-12","arxiv_id":"2107.05348","repositories_listed":2,"syntology":null},{"url":"/paper/multiple-meta-model-quantifying-for-medical","slug":"multiple-meta-model-quantifying-for-medical","title":"Multiple Meta-model Quantifying for Medical Visual Question Answering","date":"2021-05-19","arxiv_id":"2105.08913","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 3 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multiple-meta-model-quantifying-for-medical#ran","syntology_url":"https://syntology.ai/paper/2105.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08913"}},"official":{"repos":["aioz-ai/MICCAI21_MMQ"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/towards-general-purpose-vision-systems","slug":"towards-general-purpose-vision-systems","title":"Towards General Purpose Vision Systems","date":"2021-04-01","arxiv_id":"2104.00743","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-general-purpose-vision-systems#ran","syntology_url":"https://syntology.ai/paper/2104.00743","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.00743"}},"official":{"repos":["allenai/gpv-1"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-generation-of-contrast-sets-from","slug":"automatic-generation-of-contrast-sets-from","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","date":"2021-03-17","arxiv_id":"2103.09591","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"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) · 4 unverified","sample_list":"/paper/automatic-generation-of-contrast-sets-from#ran","syntology_url":"https://syntology.ai/paper/2103.09591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.09591"}},"official":{"repos":["yonatanbitton/AutoGenOfContrastSetsFromSceneGraphs"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/slake-a-semantically-labeled-knowledge","slug":"slake-a-semantically-labeled-knowledge","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","date":"2021-02-18","arxiv_id":"2102.09542","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-vision-and-language-tasks-via-text","slug":"unifying-vision-and-language-tasks-via-text","title":"Unifying Vision-and-Language Tasks via Text Generation","date":"2021-02-04","arxiv_id":"2102.02779","repositories_listed":2,"syntology":{"n":12,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":10,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/unifying-vision-and-language-tasks-via-text#ran","syntology_url":"https://syntology.ai/paper/2102.02779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.02779"}},"official":{"repos":["j-min/VL-T5"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/conceptbert-concept-aware-representation-for","slug":"conceptbert-concept-aware-representation-for","title":"ConceptBert: Concept-Aware Representation for Visual Question Answering","date":"2020-11-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/x-lxmert-paint-caption-and-answer-questions","slug":"x-lxmert-paint-caption-and-answer-questions","title":"X-LXMERT: Paint, Caption and Answer Questions with Multi-Modal Transformers","date":"2020-09-23","arxiv_id":"2009.11278","repositories_listed":2,"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/x-lxmert-paint-caption-and-answer-questions#ran","syntology_url":"https://syntology.ai/paper/2009.11278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.11278"}},"official":{"repos":["allenai/x-lxmert"],"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/mutant-a-training-paradigm-for-out-of","slug":"mutant-a-training-paradigm-for-out-of","title":"MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering","date":"2020-09-18","arxiv_id":"2009.08566","repositories_listed":2,"syntology":null},{"url":"/paper/sparse-and-continuous-attention-mechanisms","slug":"sparse-and-continuous-attention-mechanisms","title":"Sparse and Continuous Attention Mechanisms","date":"2020-06-12","arxiv_id":"2006.07214","repositories_listed":2,"syntology":{"n":15,"n_ran":12,"n_constructed":9,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 9 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sparse-and-continuous-attention-mechanisms#ran","syntology_url":"https://syntology.ai/paper/2006.07214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07214"}},"official":{"repos":["deep-spin/mcan-vqa-continuous-attention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["listed"]}}},{"url":"/paper/large-scale-adversarial-training-for-vision","slug":"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":12,"n_constructed":5,"n_ran_checked":9,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":8,"phrase":"12 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/large-scale-adversarial-training-for-vision#ran","syntology_url":"https://syntology.ai/paper/2006.06195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06195"}},"official":{"repos":["zhegan27/LXMERT-AdvTrain","zhegan27/VILLA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":9,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/x-linear-attention-networks-for-image","slug":"x-linear-attention-networks-for-image","title":"X-Linear Attention Networks for Image Captioning","date":"2020-03-31","arxiv_id":"2003.14080","repositories_listed":2,"syntology":null},{"url":"/paper/towards-ground-truth-evaluation-of-visual","slug":"towards-ground-truth-evaluation-of-visual","title":"Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI","date":"2020-03-16","arxiv_id":"2003.07258","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-ground-truth-evaluation-of-visual#ran","syntology_url":"https://syntology.ai/paper/2003.07258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07258"}},"official":{"repos":["ahmedmagdiosman/clevr-xai","ahmedmagdiosman/simply-clevr-dataset"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-samples-synthesizing-for","slug":"counterfactual-samples-synthesizing-for","title":"Counterfactual Samples Synthesizing for Robust Visual Question Answering","date":"2020-03-14","arxiv_id":"2003.06576","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/counterfactual-samples-synthesizing-for#ran","syntology_url":"https://syntology.ai/paper/2003.06576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.06576"}},"official":{"repos":["yanxinzju/CSS-VQA"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/fine-grained-image-classification-and","slug":"fine-grained-image-classification-and","title":"Fine-grained Image Classification and Retrieval by Combining Visual and Locally Pooled Textual Features","date":"2020-01-14","arxiv_id":"2001.04732","repositories_listed":2,"syntology":null},{"url":"/paper/in-defense-of-grid-features-for-visual","slug":"in-defense-of-grid-features-for-visual","title":"In Defense of Grid Features for Visual Question Answering","date":"2020-01-10","arxiv_id":"2001.03615","repositories_listed":2,"syntology":null},{"url":"/paper/large-scale-pretraining-for-visual-dialog-a","slug":"large-scale-pretraining-for-visual-dialog-a","title":"Large-scale Pretraining for Visual Dialog: A Simple State-of-the-Art Baseline","date":"2019-12-05","arxiv_id":"1912.02379","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/large-scale-pretraining-for-visual-dialog-a#ran","syntology_url":"https://syntology.ai/paper/1912.02379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02379"}},"official":{"repos":["vmurahari3/visdial-bert"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/overcoming-data-limitation-in-medical-visual","slug":"overcoming-data-limitation-in-medical-visual","title":"Overcoming Data Limitation in Medical Visual Question Answering","date":"2019-09-26","arxiv_id":"1909.11867","repositories_listed":2,"syntology":null},{"url":"/paper/omninet-a-unified-architecture-for-multi","slug":"omninet-a-unified-architecture-for-multi","title":"OmniNet: A unified architecture for multi-modal multi-task learning","date":"2019-07-17","arxiv_id":"1907.07804","repositories_listed":2,"syntology":null},{"url":"/paper/the-neuro-symbolic-concept-learner-1","slug":"the-neuro-symbolic-concept-learner-1","title":"The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision","date":"2019-04-26","arxiv_id":"1904.12584","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-neuro-symbolic-concept-learner-1#ran","syntology_url":"https://syntology.ai/paper/1904.12584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.12584"}},"official":{"repos":["vacancy/NSCL-PyTorch-Release"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/answer-them-all-toward-universal-visual","slug":"answer-them-all-toward-universal-visual","title":"Answer Them All! Toward Universal Visual Question Answering Models","date":"2019-03-01","arxiv_id":"1903.00366","repositories_listed":2,"syntology":null},{"url":"/paper/dual-attention-networks-for-visual-reference","slug":"dual-attention-networks-for-visual-reference","title":"Dual Attention Networks for Visual Reference Resolution in Visual Dialog","date":"2019-02-25","arxiv_id":"1902.09368","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dual-attention-networks-for-visual-reference#ran","syntology_url":"https://syntology.ai/paper/1902.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.09368"}},"official":{"repos":["gicheonkang/DAN-VisDial"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/learning-representations-of-sets-through","slug":"learning-representations-of-sets-through","title":"Learning Representations of Sets through Optimized Permutations","date":"2018-12-10","arxiv_id":"1812.03928","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/learning-representations-of-sets-through#ran","syntology_url":"https://syntology.ai/paper/1812.03928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.03928"}},"official":{"repos":["Cyanogenoid/perm-optim","iclr2019-anon123456/perm-optim"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-symbolic-vqa-disentangling-reasoning","slug":"neural-symbolic-vqa-disentangling-reasoning","title":"Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding","date":"2018-10-04","arxiv_id":"1810.02338","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-symbolic-vqa-disentangling-reasoning#ran","syntology_url":"https://syntology.ai/paper/1810.02338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02338"}},"official":null}},{"url":"/paper/end-to-end-audio-visual-scene-aware-dialog","slug":"end-to-end-audio-visual-scene-aware-dialog","title":"End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features","date":"2018-06-21","arxiv_id":"1806.08409","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/end-to-end-audio-visual-scene-aware-dialog#ran","syntology_url":"https://syntology.ai/paper/1806.08409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.08409"}},"official":null}},{"url":"/paper/focal-visual-text-attention-for-visual","slug":"focal-visual-text-attention-for-visual","title":"Focal Visual-Text Attention for Visual Question Answering","date":"2018-06-05","arxiv_id":"1806.01873","repositories_listed":2,"syntology":null},{"url":"/paper/ai2-thor-an-interactive-3d-environment-for","slug":"ai2-thor-an-interactive-3d-environment-for","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","date":"2017-12-14","arxiv_id":"1712.05474","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ai2-thor-an-interactive-3d-environment-for#ran","syntology_url":"https://syntology.ai/paper/1712.05474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.05474"}},"official":{"repos":["allenai/ai2thor"],"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":["official"]}}},{"url":"/paper/beyond-bilinear-generalized-multi-modal","slug":"beyond-bilinear-generalized-multi-modal","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","date":"2017-08-10","arxiv_id":"1708.03619","repositories_listed":2,"syntology":null},{"url":"/paper/modulating-early-visual-processing-by","slug":"modulating-early-visual-processing-by","title":"Modulating early visual processing by language","date":"2017-07-02","arxiv_id":"1707.00683","repositories_listed":2,"syntology":null},{"url":"/paper/tgif-qa-toward-spatio-temporal-reasoning-in","slug":"tgif-qa-toward-spatio-temporal-reasoning-in","title":"TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering","date":"2017-04-14","arxiv_id":"1704.04497","repositories_listed":2,"syntology":null},{"url":"/paper/grad-cam-why-did-you-say-that","slug":"grad-cam-why-did-you-say-that","title":"Grad-CAM: Why did you say that?","date":"2016-11-22","arxiv_id":"1611.07450","repositories_listed":2,"syntology":null},{"url":"/paper/dual-attention-networks-for-multimodal","slug":"dual-attention-networks-for-multimodal","title":"Dual Attention Networks for Multimodal Reasoning and Matching","date":"2016-11-02","arxiv_id":"1611.00471","repositories_listed":2,"syntology":null},{"url":"/paper/neural-module-networks","slug":"neural-module-networks","title":"Neural Module Networks","date":"2015-11-09","arxiv_id":"1511.02799","repositories_listed":2,"syntology":null},{"url":"/paper/describe-anything-model-for-visual-question","slug":"describe-anything-model-for-visual-question","title":"Describe Anything Model for Visual Question Answering on Text-rich Images","date":"2025-07-16","arxiv_id":"2507.12441","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-cropa-a-reproducibility-study-and","slug":"revisiting-cropa-a-reproducibility-study-and","title":"Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models","date":"2025-06-28","arxiv_id":"2506.22982","repositories_listed":1,"syntology":null},{"url":"/paper/drishtikon-multi-granular-visual-grounding","slug":"drishtikon-multi-granular-visual-grounding","title":"DrishtiKon: Multi-Granular Visual Grounding for Text-Rich Document Images","date":"2025-06-26","arxiv_id":"2506.21316","repositories_listed":1,"syntology":null},{"url":"/paper/hribench-benchmarking-vision-language-models","slug":"hribench-benchmarking-vision-language-models","title":"HRIBench: Benchmarking Vision-Language Models for Real-Time Human Perception in Human-Robot Interaction","date":"2025-06-25","arxiv_id":"2506.20566","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-lightweight-vision-language-models","slug":"adapting-lightweight-vision-language-models","title":"Adapting Lightweight Vision Language Models for Radiological Visual Question Answering","date":"2025-06-17","arxiv_id":"2506.14451","repositories_listed":1,"syntology":null},{"url":"/paper/simpledoc-multi-modal-document-understanding","slug":"simpledoc-multi-modal-document-understanding","title":"SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinement","date":"2025-06-16","arxiv_id":"2506.14035","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpledoc-multi-modal-document-understanding#ran","syntology_url":"https://syntology.ai/paper/2506.14035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.14035"}},"official":{"repos":["ag2ai/simpledoc"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"43cf22b952d06a7ab8523bc5a068ec8b021137dc7dc3431381fc72ba5fce60db","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}