{"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-instruction-following","name":"visual instruction following","slug":"visual-instruction-following","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":24,"papers_with_code":14,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/visual-instruction-following-on-llava-bench","slug":"visual-instruction-following-on-llava-bench","dataset":"LLaVA-Bench","dataset_url":"/dataset/llava-bench-in-the-wild","rows_in_archive":8,"metrics":["avg score"],"first_row_in_archive_order":{"model":"CuMo-7B","paper_title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","paper_url":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled","paper_date":"2024-05-09","arxiv_id":"2405.05949","code_links":[{"title":"shi-labs/cumo","url":"https://github.com/shi-labs/cumo"}],"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}},"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/llava-bench-in-the-wild","name":"LLaVA-Bench","full_name":"","num_papers_in_archive":130},{"url":"/dataset/vstar-1m","name":"VSTaR-1M","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/instruction-following","name":"Instruction Following"}],"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":1,"rows_per_page":100,"shown":24,"of":24,"of_with_code":14,"tagged_in_all":24,"counts":{"archive_papers_tagged":24,"with_a_code_link":14,"where_syntology_ran_a_sample":9,"not_listed_spam_title":0,"listed":24,"listed_where_code_ran":9,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":7,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":7,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/blip-2-bootstrapping-language-image-pre","slug":"blip-2-bootstrapping-language-image-pre","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","date":"2023-01-30","arxiv_id":"2301.12597","repositories_listed":17,"syntology":{"n":8,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 4 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) · 4 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/blip-2-bootstrapping-language-image-pre#ran","syntology_url":"https://syntology.ai/paper/2301.12597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12597"}},"official":{"repos":["salesforce/lavis"],"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/visual-instruction-tuning-1","slug":"visual-instruction-tuning-1","title":"Visual Instruction Tuning","date":"2023-04-17","arxiv_id":"2304.08485","repositories_listed":13,"syntology":{"n":51,"n_ran":16,"n_constructed":6,"n_ran_checked":8,"n_instrument":8,"n_unverified":35,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":0,"phrase":"16 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/visual-instruction-tuning-1#ran","syntology_url":"https://syntology.ai/paper/2304.08485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08485"}},"official":{"repos":["haotian-liu/LLaVA"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["community","listed","named_in_paper","official"]}}},{"url":"/paper/improved-baselines-with-visual-instruction","slug":"improved-baselines-with-visual-instruction","title":"Improved Baselines with Visual Instruction Tuning","date":"2023-10-05","arxiv_id":"2310.03744","repositories_listed":9,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":8,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/improved-baselines-with-visual-instruction#ran","syntology_url":"https://syntology.ai/paper/2310.03744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.03744"}},"official":null}},{"url":"/paper/instructblip-towards-general-purpose-vision","slug":"instructblip-towards-general-purpose-vision","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","date":"2023-05-11","arxiv_id":"2305.06500","repositories_listed":4,"syntology":null},{"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/geoground-a-unified-large-vision-language","slug":"geoground-a-unified-large-vision-language","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","date":"2024-11-16","arxiv_id":"2411.11904","repositories_listed":1,"syntology":null},{"url":"/paper/mpoxvlm-a-vision-language-model-for","slug":"mpoxvlm-a-vision-language-model-for","title":"MpoxVLM: A Vision-Language Model for Diagnosing Skin Lesions from Mpox Virus Infection","date":"2024-11-16","arxiv_id":"2411.10888","repositories_listed":1,"syntology":null},{"url":"/paper/mmsci-a-multimodal-multi-discipline-dataset","slug":"mmsci-a-multimodal-multi-discipline-dataset","title":"MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding","date":"2024-07-06","arxiv_id":"2407.04903","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":16,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mmsci-a-multimodal-multi-discipline-dataset#ran","syntology_url":"https://syntology.ai/paper/2407.04903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04903"}},"official":{"repos":["leezekun/mmsci"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/milora-harnessing-minor-singular-components","slug":"milora-harnessing-minor-singular-components","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","date":"2024-06-13","arxiv_id":"2406.09044","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/milora-harnessing-minor-singular-components#ran","syntology_url":"https://syntology.ai/paper/2406.09044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09044"}},"official":{"repos":["graphpku/pissa"],"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/cumo-scaling-multimodal-llm-with-co-upcycled","slug":"cumo-scaling-multimodal-llm-with-co-upcycled","title":"CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts","date":"2024-05-09","arxiv_id":"2405.05949","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":2,"n_instrument":9,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cumo-scaling-multimodal-llm-with-co-upcycled#ran","syntology_url":"https://syntology.ai/paper/2405.05949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.05949"}},"official":{"repos":["shi-labs/cumo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/chain-of-spot-interactive-reasoning-improves","slug":"chain-of-spot-interactive-reasoning-improves","title":"Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models","date":"2024-03-19","arxiv_id":"2403.12966","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/chain-of-spot-interactive-reasoning-improves#ran","syntology_url":"https://syntology.ai/paper/2403.12966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12966"}},"official":{"repos":["dongyh20/chain-of-spot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vim-probing-multimodal-large-language-models","slug":"vim-probing-multimodal-large-language-models","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","date":"2023-11-29","arxiv_id":"2311.17647","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vim-probing-multimodal-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2311.17647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17647"}},"official":{"repos":["vim-bench/vim_tool"],"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/sharegpt4v-improving-large-multi-modal-models","slug":"sharegpt4v-improving-large-multi-modal-models","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","date":"2023-11-21","arxiv_id":"2311.12793","repositories_listed":1,"syntology":null},{"url":"/paper/instruction-clarification-requests-in","slug":"instruction-clarification-requests-in","title":"Instruction Clarification Requests in Multimodal Collaborative Dialogue Games: Tasks, and an Analysis of the CoDraw Dataset","date":"2023-02-28","arxiv_id":"2302.14406","repositories_listed":1,"syntology":null},{"url":null,"slug":"do-we-really-need-visual-instructions-towards","title":"Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models","date":"2025-02-17","arxiv_id":"2502.11427","repositories_listed":0,"syntology":null},{"url":null,"slug":"m4cxr-exploring-multi-task-potentials-of","title":"M4CXR: Exploring Multi-task Potentials of Multi-modal Large Language Models for Chest X-ray Interpretation","date":"2024-08-29","arxiv_id":"2408.16213","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-a-foundation-model-for-space-based","title":"Space-LLaVA: a Vision-Language Model Adapted to Extraterrestrial Applications","date":"2024-08-12","arxiv_id":"2408.05924","repositories_listed":0,"syntology":null},{"url":null,"slug":"lvlm-empowered-multi-modal-representation","title":"LVLM-empowered Multi-modal Representation Learning for Visual Place Recognition","date":"2024-07-09","arxiv_id":"2407.06730","repositories_listed":0,"syntology":null},{"url":null,"slug":"pelican-correcting-hallucination-in-vision","title":"Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification","date":"2024-07-02","arxiv_id":"2407.02352","repositories_listed":0,"syntology":null},{"url":null,"slug":"reminding-multimodal-large-language-models-of","title":"Reminding Multimodal Large Language Models of Object-aware Knowledge with Retrieved Tags","date":"2024-06-16","arxiv_id":"2406.10839","repositories_listed":0,"syntology":null},{"url":null,"slug":"facegpt-self-supervised-learning-to-chat","title":"FaceGPT: Self-supervised Learning to Chat about 3D Human Faces","date":"2024-06-11","arxiv_id":"2406.07163","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-embeddings-for-graph-instruction-tuning","title":"Joint Embeddings for Graph Instruction Tuning","date":"2024-05-31","arxiv_id":"2405.20684","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrected-multimodal-large-language","title":"Self-Corrected Multimodal Large Language Model for End-to-End Robot Manipulation","date":"2024-05-27","arxiv_id":"2405.17418","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-tuning-large-vision-language-models-as","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","date":"2024-05-16","arxiv_id":"2405.10292","repositories_listed":0,"syntology":null}],"syntology_records":9,"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":9,"papers_where_code_ran_first_page":"/task/visual-instruction-following/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":"ran","page":1,"of":1,"url":"/task/visual-instruction-following/papers/ran/1","json":"/task/visual-instruction-following/papers/ran/1.json","rows":9}],"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":"301c572d36eebe9f12b79c7faab12387b530ef0e0c7bc4a604128d8984abe157","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}