{"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":10,"n_unverified":2,"n_pointer_only":0}}}],"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":24,"items":[{"url":"/paper/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_unverified":4,"n_pointer_only":1}},{"url":"/paper/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_unverified":35,"n_pointer_only":0}},{"url":"/paper/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_unverified":3,"n_pointer_only":8}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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/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/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_unverified":5,"n_pointer_only":16}},{"url":"/paper/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_unverified":0,"n_pointer_only":1}},{"url":"/paper/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":10,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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}],"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"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-25T09:33:49+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}