{"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/multimodal-large-language-model/papers/2","list_of":"/task/multimodal-large-language-model","task":"Multimodal Large Language Model","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":4,"rows_per_page":100,"rows":[101,200],"of":347,"counts":{"archive_papers_tagged":347,"with_a_code_link":160,"where_syntology_ran_a_sample":59,"not_listed_spam_title":0,"listed":347,"listed_where_code_ran":59,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":51,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":51,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/multimodal-large-language-model","prev":"/task/multimodal-large-language-model","next":"/task/multimodal-large-language-model/papers/3","papers":[{"url":"/paper/seeing-and-understanding-bridging-vision-with","slug":"seeing-and-understanding-bridging-vision-with","title":"ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area","date":"2024-08-14","arxiv_id":"2408.07246","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"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) · 0 unverified","sample_list":"/paper/seeing-and-understanding-bridging-vision-with#ran","syntology_url":"https://syntology.ai/paper/2408.07246","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.07246"}},"official":{"repos":["AI4Chem/ChemVlm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vita-towards-open-source-interactive-omni","slug":"vita-towards-open-source-interactive-omni","title":"VITA: Towards Open-Source Interactive Omni Multimodal LLM","date":"2024-08-09","arxiv_id":"2408.05211","repositories_listed":1,"syntology":null},{"url":"/paper/videoqa-in-the-era-of-llms-an-empirical-study","slug":"videoqa-in-the-era-of-llms-an-empirical-study","title":"VideoQA in the Era of LLMs: An Empirical Study","date":"2024-08-08","arxiv_id":"2408.04223","repositories_listed":1,"syntology":null},{"url":"/paper/2408-02544","slug":"2408-02544","title":"Caution for the Environment: Multimodal Agents are Susceptible to Environmental Distractions","date":"2024-08-05","arxiv_id":"2408.02544","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":16,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/2408-02544#ran","syntology_url":"https://syntology.ai/paper/2408.02544","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02544"}},"official":{"repos":["xbmxb/EnvDistraction"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/inf-llava-dual-perspective-perception-for","slug":"inf-llava-dual-perspective-perception-for","title":"INF-LLaVA: Dual-perspective Perception for High-Resolution Multimodal Large Language Model","date":"2024-07-23","arxiv_id":"2407.16198","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/inf-llava-dual-perspective-perception-for#ran","syntology_url":"https://syntology.ai/paper/2407.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16198"}},"official":{"repos":["weihuanglin/inf-llava"],"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","unlocated"]}}},{"url":"/paper/t2v-compbench-a-comprehensive-benchmark-for","slug":"t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","arxiv_id":"2407.14505","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/t2v-compbench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.14505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14505"}},"official":{"repos":["KaiyueSun98/T2V-CompBench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-text-generation-in-the-wild","slug":"visual-text-generation-in-the-wild","title":"Visual Text Generation in the Wild","date":"2024-07-19","arxiv_id":"2407.14138","repositories_listed":1,"syntology":null},{"url":"/paper/urbanworld-an-urban-world-model-for-3d-city","slug":"urbanworld-an-urban-world-model-for-3d-city","title":"UrbanWorld: An Urban World Model for 3D City Generation","date":"2024-07-16","arxiv_id":"2407.11965","repositories_listed":1,"syntology":null},{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-refer-and-ground-multimodal-large-language","slug":"a-refer-and-ground-multimodal-large-language","title":"A Refer-and-Ground Multimodal Large Language Model for Biomedicine","date":"2024-06-26","arxiv_id":"2406.18146","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":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) · 1 unverified","sample_list":"/paper/a-refer-and-ground-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2406.18146","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18146"}},"official":{"repos":["shawnhuang497/bird"],"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/dalpsr-leverage-degradation-aligned-language","slug":"dalpsr-leverage-degradation-aligned-language","title":"DaLPSR: Leverage Degradation-Aligned Language Prompt for Real-World Image Super-Resolution","date":"2024-06-24","arxiv_id":"2406.16477","repositories_listed":1,"syntology":null},{"url":"/paper/llasa-large-multimodal-agent-for-human","slug":"llasa-large-multimodal-agent-for-human","title":"LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors","date":"2024-06-20","arxiv_id":"2406.14498","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/llasa-large-multimodal-agent-for-human#ran","syntology_url":"https://syntology.ai/paper/2406.14498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14498"}},"official":{"repos":["bashlab/llasa"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/holmes-vad-towards-unbiased-and-explainable","slug":"holmes-vad-towards-unbiased-and-explainable","title":"Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM","date":"2024-06-18","arxiv_id":"2406.12235","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/holmes-vad-towards-unbiased-and-explainable#ran","syntology_url":"https://syntology.ai/paper/2406.12235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12235"}},"official":{"repos":["pipixin321/holmesvad"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/mmneuron-discovering-neuron-level-domain","slug":"mmneuron-discovering-neuron-level-domain","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","date":"2024-06-17","arxiv_id":"2406.11193","repositories_listed":1,"syntology":null},{"url":"/paper/explore-the-limits-of-omni-modal-pretraining","slug":"explore-the-limits-of-omni-modal-pretraining","title":"Explore the Limits of Omni-modal Pretraining at Scale","date":"2024-06-13","arxiv_id":"2406.09412","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-table-understanding","slug":"multimodal-table-understanding","title":"Multimodal Table Understanding","date":"2024-06-12","arxiv_id":"2406.08100","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multimodal-table-understanding#ran","syntology_url":"https://syntology.ai/paper/2406.08100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08100"}},"official":{"repos":["spursgozmy/table-llava"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visionllm-v2-an-end-to-end-generalist","slug":"visionllm-v2-an-end-to-end-generalist","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","date":"2024-06-12","arxiv_id":"2406.08394","repositories_listed":1,"syntology":null},{"url":"/paper/trins-towards-multimodal-language-models-that","slug":"trins-towards-multimodal-language-models-that","title":"TRINS: Towards Multimodal Language Models that Can Read","date":"2024-06-10","arxiv_id":"2406.06730","repositories_listed":1,"syntology":null},{"url":"/paper/vip-versatile-image-outpainting-empowered-by","slug":"vip-versatile-image-outpainting-empowered-by","title":"VIP: Versatile Image Outpainting Empowered by Multimodal Large Language Model","date":"2024-06-03","arxiv_id":"2406.01059","repositories_listed":1,"syntology":null},{"url":"/paper/voice-jailbreak-attacks-against-gpt-4o","slug":"voice-jailbreak-attacks-against-gpt-4o","title":"Voice Jailbreak Attacks Against GPT-4o","date":"2024-05-29","arxiv_id":"2405.19103","repositories_listed":1,"syntology":null},{"url":"/paper/visual-anchors-are-strong-information","slug":"visual-anchors-are-strong-information","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","date":"2024-05-28","arxiv_id":"2405.17815","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-multimodal-large-language-model","slug":"a-survey-of-multimodal-large-language-model","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","date":"2024-05-26","arxiv_id":"2405.16640","repositories_listed":1,"syntology":null},{"url":"/paper/v-zen-efficient-gui-understanding-and-precise","slug":"v-zen-efficient-gui-understanding-and-precise","title":"V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM","date":"2024-05-24","arxiv_id":"2405.15341","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-pixel-advancing-long-context","slug":"from-text-to-pixel-advancing-long-context","title":"From Text to Pixel: Advancing Long-Context Understanding in MLLMs","date":"2024-05-23","arxiv_id":"2405.14213","repositories_listed":1,"syntology":null},{"url":"/paper/hunyuan-dit-a-powerful-multi-resolution","slug":"hunyuan-dit-a-powerful-multi-resolution","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","date":"2024-05-14","arxiv_id":"2405.08748","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"8 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/hunyuan-dit-a-powerful-multi-resolution#ran","syntology_url":"https://syntology.ai/paper/2405.08748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.08748"}},"official":{"repos":["tencent/hunyuandit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/layout-generation-agents-with-large-language","slug":"layout-generation-agents-with-large-language","title":"Layout Generation Agents with Large Language Models","date":"2024-05-13","arxiv_id":"2405.08037","repositories_listed":1,"syntology":null},{"url":"/paper/seed-data-edit-technical-report-a-hybrid","slug":"seed-data-edit-technical-report-a-hybrid","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","date":"2024-05-07","arxiv_id":"2405.04007","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"7 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/seed-data-edit-technical-report-a-hybrid#ran","syntology_url":"https://syntology.ai/paper/2405.04007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.04007"}},"official":{"repos":["ailab-cvc/seed-x"],"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/paint-by-inpaint-learning-to-add-image","slug":"paint-by-inpaint-learning-to-add-image","title":"Paint by Inpaint: Learning to Add Image Objects by Removing Them First","date":"2024-04-28","arxiv_id":"2404.18212","repositories_listed":1,"syntology":null},{"url":"/paper/worldgpt-empowering-llm-as-multimodal-world","slug":"worldgpt-empowering-llm-as-multimodal-world","title":"WorldGPT: Empowering LLM as Multimodal World Model","date":"2024-04-28","arxiv_id":"2404.18202","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"5 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/worldgpt-empowering-llm-as-multimodal-world#ran","syntology_url":"https://syntology.ai/paper/2404.18202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18202"}},"official":{"repos":["dcdmllm/worldgpt"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/how-far-are-we-to-gpt-4v-closing-the-gap-to","slug":"how-far-are-we-to-gpt-4v-closing-the-gap-to","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","date":"2024-04-25","arxiv_id":"2404.16821","repositories_listed":1,"syntology":null},{"url":"/paper/groma-localized-visual-tokenization-for","slug":"groma-localized-visual-tokenization-for","title":"Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models","date":"2024-04-19","arxiv_id":"2404.13013","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/groma-localized-visual-tokenization-for#ran","syntology_url":"https://syntology.ai/paper/2404.13013","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.13013"}},"official":{"repos":["FoundationVision/Groma"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-learning-and-llm-based-methods-applied","slug":"deep-learning-and-llm-based-methods-applied","title":"Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification","date":"2024-04-16","arxiv_id":"2404.10757","repositories_listed":1,"syntology":null},{"url":"/paper/lavy-vietnamese-multimodal-large-language","slug":"lavy-vietnamese-multimodal-large-language","title":"LaVy: Vietnamese Multimodal Large Language Model","date":"2024-04-11","arxiv_id":"2404.07922","repositories_listed":1,"syntology":null},{"url":"/paper/umbrae-unified-multimodal-decoding-of-brain","slug":"umbrae-unified-multimodal-decoding-of-brain","title":"UMBRAE: Unified Multimodal Brain Decoding","date":"2024-04-10","arxiv_id":"2404.07202","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/umbrae-unified-multimodal-decoding-of-brain#ran","syntology_url":"https://syntology.ai/paper/2404.07202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07202"}},"official":{"repos":["weihaox/UMBRAE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/moma-multimodal-llm-adapter-for-fast","slug":"moma-multimodal-llm-adapter-for-fast","title":"MoMA: Multimodal LLM Adapter for Fast Personalized Image Generation","date":"2024-04-08","arxiv_id":"2404.05674","repositories_listed":1,"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/moma-multimodal-llm-adapter-for-fast#ran","syntology_url":"https://syntology.ai/paper/2404.05674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.05674"}},"official":{"repos":["bytedance/MoMA"],"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/lite-modeling-environmental-ecosystems-with","slug":"lite-modeling-environmental-ecosystems-with","title":"LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models","date":"2024-04-01","arxiv_id":"2404.01165","repositories_listed":1,"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/lite-modeling-environmental-ecosystems-with#ran","syntology_url":"https://syntology.ai/paper/2404.01165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01165"}},"official":{"repos":["hrlics/lite"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/draw-and-understand-leveraging-visual-prompts","slug":"draw-and-understand-leveraging-visual-prompts","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","date":"2024-03-29","arxiv_id":"2403.20271","repositories_listed":1,"syntology":null},{"url":"/paper/cat-enhancing-multimodal-large-language-model","slug":"cat-enhancing-multimodal-large-language-model","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2024-03-07","arxiv_id":"2403.04640","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/cat-enhancing-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2403.04640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04640"}},"official":{"repos":["rikeilong/bay-cat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-modal-instruction-tuned-llms-with-fine","slug":"multi-modal-instruction-tuned-llms-with-fine","title":"Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception","date":"2024-03-05","arxiv_id":"2403.02969","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi-modal-instruction-tuned-llms-with-fine#ran","syntology_url":"https://syntology.ai/paper/2403.02969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02969"}},"official":{"repos":["jwh97nn/anyref"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-assisted-multi-teacher-continual-learning","slug":"llm-assisted-multi-teacher-continual-learning","title":"LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery","date":"2024-02-26","arxiv_id":"2402.16664","repositories_listed":1,"syntology":null},{"url":"/paper/agent-smith-a-single-image-can-jailbreak-one","slug":"agent-smith-a-single-image-can-jailbreak-one","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","date":"2024-02-13","arxiv_id":"2402.08567","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/agent-smith-a-single-image-can-jailbreak-one#ran","syntology_url":"https://syntology.ai/paper/2402.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08567"}},"official":{"repos":["sail-sg/agent-smith"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gerea-question-aware-prompt-captions-for","slug":"gerea-question-aware-prompt-captions-for","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","date":"2024-02-04","arxiv_id":"2402.02503","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gerea-question-aware-prompt-captions-for#ran","syntology_url":"https://syntology.ai/paper/2402.02503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02503"}},"official":{"repos":["upper9527/gerea"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mementos-a-comprehensive-benchmark-for","slug":"mementos-a-comprehensive-benchmark-for","title":"Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences","date":"2024-01-19","arxiv_id":"2401.10529","repositories_listed":1,"syntology":null},{"url":"/paper/lion-empowering-multimodal-large-language-1","slug":"lion-empowering-multimodal-large-language-1","title":"LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/allspark-a-multimodal-spatiotemporal-general","slug":"allspark-a-multimodal-spatiotemporal-general","title":"AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Ten Modalities via Language as a Reference Framework","date":"2023-12-31","arxiv_id":"2401.00546","repositories_listed":1,"syntology":null},{"url":"/paper/starvector-generating-scalable-vector","slug":"starvector-generating-scalable-vector","title":"StarVector: Generating Scalable Vector Graphics Code from Images and Text","date":"2023-12-17","arxiv_id":"2312.11556","repositories_listed":1,"syntology":null},{"url":"/paper/hallucination-augmented-contrastive-learning","slug":"hallucination-augmented-contrastive-learning","title":"Hallucination Augmented Contrastive Learning for Multimodal Large Language Model","date":"2023-12-12","arxiv_id":"2312.06968","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"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) · 3 unverified","sample_list":"/paper/hallucination-augmented-contrastive-learning#ran","syntology_url":"https://syntology.ai/paper/2312.06968","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06968"}},"official":{"repos":["x-plug/mplug-halowl"],"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","unlocated"]}}},{"url":"/paper/mplug-paperowl-scientific-diagram-analysis","slug":"mplug-paperowl-scientific-diagram-analysis","title":"mPLUG-PaperOwl: Scientific Diagram Analysis with the Multimodal Large Language Model","date":"2023-11-30","arxiv_id":"2311.18248","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mplug-paperowl-scientific-diagram-analysis#ran","syntology_url":"https://syntology.ai/paper/2311.18248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.18248"}},"official":{"repos":["x-plug/mplug-docowl"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/llmga-multimodal-large-language-model-based","slug":"llmga-multimodal-large-language-model-based","title":"LLMGA: Multimodal Large Language Model based Generation Assistant","date":"2023-11-27","arxiv_id":"2311.16500","repositories_listed":1,"syntology":null},{"url":"/paper/lion-empowering-multimodal-large-language","slug":"lion-empowering-multimodal-large-language","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","date":"2023-11-20","arxiv_id":"2311.11860","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lion-empowering-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2311.11860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.11860"}},"official":{"repos":["rshaojimmy/jiutian"],"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/chain-of-images-for-intuitively-reasoning","slug":"chain-of-images-for-intuitively-reasoning","title":"Chain of Images for Intuitively Reasoning","date":"2023-11-09","arxiv_id":"2311.09241","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-chatgpt-for-medical-applications","slug":"multimodal-chatgpt-for-medical-applications","title":"Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V","date":"2023-10-29","arxiv_id":"2310.19061","repositories_listed":1,"syntology":null},{"url":"/paper/cxr-llava-multimodal-large-language-model-for","slug":"cxr-llava-multimodal-large-language-model-for","title":"CXR-LLAVA: a multimodal large language model for interpreting chest X-ray images","date":"2023-10-22","arxiv_id":"2310.18341","repositories_listed":1,"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":3,"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/cxr-llava-multimodal-large-language-model-for#ran","syntology_url":"https://syntology.ai/paper/2310.18341","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18341"}},"official":{"repos":["ecofri/cxr_llava"],"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/ureader-universal-ocr-free-visually-situated","slug":"ureader-universal-ocr-free-visually-situated","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","date":"2023-10-08","arxiv_id":"2310.05126","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ureader-universal-ocr-free-visually-situated#ran","syntology_url":"https://syntology.ai/paper/2310.05126","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05126"}},"official":{"repos":["lukeforeveryoung/ureader"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/finvis-gpt-a-multimodal-large-language-model","slug":"finvis-gpt-a-multimodal-large-language-model","title":"FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis","date":"2023-07-31","arxiv_id":"2308.01430","repositories_listed":1,"syntology":null},{"url":"/paper/mplug-docowl-modularized-multimodal-large","slug":"mplug-docowl-modularized-multimodal-large","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","date":"2023-07-04","arxiv_id":"2307.02499","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-multimodal-large-language-models","slug":"a-survey-on-multimodal-large-language-models","title":"A Survey on Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13549","repositories_listed":1,"syntology":null},{"url":"/paper/youku-mplug-a-10-million-large-scale-chinese","slug":"youku-mplug-a-10-million-large-scale-chinese","title":"Youku-mPLUG: A 10 Million Large-scale Chinese Video-Language Dataset for Pre-training and Benchmarks","date":"2023-06-07","arxiv_id":"2306.04362","repositories_listed":1,"syntology":{"n":13,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/youku-mplug-a-10-million-large-scale-chinese#ran","syntology_url":"https://syntology.ai/paper/2306.04362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.04362"}},"official":{"repos":["x-plug/youku-mplug"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/lmeye-an-interactive-perception-network-for","slug":"lmeye-an-interactive-perception-network-for","title":"LMEye: An Interactive Perception Network for Large Language Models","date":"2023-05-05","arxiv_id":"2305.03701","repositories_listed":1,"syntology":null},{"url":"/paper/language-is-not-all-you-need-aligning-1","slug":"language-is-not-all-you-need-aligning-1","title":"Language Is Not All You Need: Aligning Perception with Language Models","date":"2023-02-27","arxiv_id":"2302.14045","repositories_listed":1,"syntology":null},{"url":null,"slug":"kptllm-towards-generic-keypoint-comprehension","title":"KptLLM++: Towards Generic Keypoint Comprehension with Large Language Model","date":"2025-07-15","arxiv_id":"2507.11102","repositories_listed":0,"syntology":null},{"url":null,"slug":"lrmr-llm-driven-relational-multi-node-ranking","title":"LRMR: LLM-Driven Relational Multi-node Ranking for Lymph Node Metastasis Assessment in Rectal Cancer","date":"2025-07-15","arxiv_id":"2507.11457","repositories_listed":0,"syntology":null},{"url":null,"slug":"chat-with-ai-the-surprising-turn-of-real-time","title":"Chat with AI: The Surprising Turn of Real-time Video Communication from Human to AI","date":"2025-07-14","arxiv_id":"2507.10510","repositories_listed":0,"syntology":null},{"url":null,"slug":"bluelm-2-5-3b-technical-report","title":"BlueLM-2.5-3B Technical Report","date":"2025-07-08","arxiv_id":"2507.05934","repositories_listed":0,"syntology":null},{"url":null,"slug":"talkfashion-intelligent-virtual-try-on","title":"TalkFashion: Intelligent Virtual Try-On Assistant Based on Multimodal Large Language Model","date":"2025-07-08","arxiv_id":"2507.05790","repositories_listed":0,"syntology":null},{"url":null,"slug":"cot-lized-diffusion-let-s-reinforce-t2i","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","date":"2025-07-06","arxiv_id":"2507.04451","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-aware-text-to-image-retrieval-referring","title":"Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval","date":"2025-06-28","arxiv_id":"2506.22864","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamjourney-perpetual-view-generation-with","title":"DreamJourney: Perpetual View Generation with Video Diffusion Models","date":"2025-06-21","arxiv_id":"2506.17705","repositories_listed":0,"syntology":null},{"url":null,"slug":"ascd-attention-steerable-contrastive-decoding","title":"ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM","date":"2025-06-17","arxiv_id":"2506.14766","repositories_listed":0,"syntology":null},{"url":null,"slug":"cfbenchmark-mm-chinese-financial-assistant","title":"CFBenchmark-MM: Chinese Financial Assistant Benchmark for Multimodal Large Language Model","date":"2025-06-16","arxiv_id":"2506.13055","repositories_listed":0,"syntology":null},{"url":null,"slug":"vgr-visual-grounded-reasoning","title":"VGR: Visual Grounded Reasoning","date":"2025-06-13","arxiv_id":"2506.11991","repositories_listed":0,"syntology":null},{"url":null,"slug":"phrased-phrase-dictionary-biasing-for-speech","title":"PHRASED: Phrase Dictionary Biasing for Speech Translation","date":"2025-06-10","arxiv_id":"2506.09175","repositories_listed":0,"syntology":null},{"url":null,"slug":"parking-perception-and-retail-street-level","title":"Parking, Perception, and Retail: Street-Level Determinants of Community Vitality in Harbin","date":"2025-06-05","arxiv_id":"2506.05080","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ntnu-system-at-the-s-i-challenge-2025-sla","title":"The NTNU System at the S&I Challenge 2025 SLA Open Track","date":"2025-06-05","arxiv_id":"2506.05121","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-llm-centric-multimodal-fusion-a-1","title":"Towards LLM-Centric Multimodal Fusion: A Survey on Integration Strategies and Techniques","date":"2025-06-05","arxiv_id":"2506.04788","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-data-augmentation-approach-for","title":"A Novel Data Augmentation Approach for Automatic Speaking Assessment on Opinion Expressions","date":"2025-06-04","arxiv_id":"2506.04077","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-street-views-to-urban-science","title":"From Street Views to Urban Science: Discovering Road Safety Factors with Multimodal Large Language Models","date":"2025-06-02","arxiv_id":"2506.02242","repositories_listed":0,"syntology":null},{"url":null,"slug":"s4-driver-scalable-self-supervised-driving","title":"S4-Driver: Scalable Self-Supervised Driving Multimodal Large Language Modelwith Spatio-Temporal Visual Representation","date":"2025-05-30","arxiv_id":"2505.24139","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniresponse-online-multimodal-conversational","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","date":"2025-05-27","arxiv_id":"2505.21724","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-before-you-diffuse-llms-guided-physics","title":"Think Before You Diffuse: LLMs-Guided Physics-Aware Video Generation","date":"2025-05-27","arxiv_id":"2505.21653","repositories_listed":0,"syntology":null},{"url":null,"slug":"guard-me-if-you-know-me-protecting-specific","title":"Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes","date":"2025-05-26","arxiv_id":"2505.19582","repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-guided-vlm-fine-tuning-with-joint","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","date":"2025-05-26","arxiv_id":"2505.19707","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-changed-detecting-and-evaluating","title":"What Changed? Detecting and Evaluating Instruction-Guided Image Edits with Multimodal Large Language Models","date":"2025-05-26","arxiv_id":"2505.20405","repositories_listed":0,"syntology":null},{"url":null,"slug":"openhoi-open-world-hand-object-interaction","title":"OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model","date":"2025-05-25","arxiv_id":"2505.18947","repositories_listed":0,"syntology":null},{"url":null,"slug":"holollm-multisensory-foundation-model-for","title":"HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning","date":"2025-05-23","arxiv_id":"2505.17645","repositories_listed":0,"syntology":null},{"url":null,"slug":"llada-v-large-language-diffusion-models-with","title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","date":"2025-05-22","arxiv_id":"2505.16933","repositories_listed":0,"syntology":null},{"url":"/paper/highlighting-what-matters-promptable","slug":"highlighting-what-matters-promptable","title":"Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval","date":"2025-05-21","arxiv_id":"2505.15877","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-centered-interactive-learning-via-mllms-1","title":"Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification","date":"2025-05-21","arxiv_id":"2506.11036","repositories_listed":0,"syntology":null},{"url":null,"slug":"miku-pal-an-automated-and-standardized-multi","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","date":"2025-05-21","arxiv_id":"2505.15772","repositories_listed":0,"syntology":null},{"url":null,"slug":"cafes-a-collaborative-multi-agent-framework","title":"CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring","date":"2025-05-20","arxiv_id":"2505.13965","repositories_listed":0,"syntology":null},{"url":null,"slug":"unigen-enhanced-training-test-time-strategies","title":"UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation","date":"2025-05-20","arxiv_id":"2505.14682","repositories_listed":0,"syntology":null},{"url":null,"slug":"univg-r1-reasoning-guided-universal-visual","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14231","repositories_listed":0,"syntology":null},{"url":null,"slug":"orqa-a-benchmark-and-foundation-model-for","title":"ORQA: A Benchmark and Foundation Model for Holistic Operating Room Modeling","date":"2025-05-19","arxiv_id":"2505.12890","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-retrieval-joint-supervision-and","title":"Beyond Retrieval: Joint Supervision and Multimodal Document Ranking for Textbook Question Answering","date":"2025-05-17","arxiv_id":"2505.13520","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-your-multimodal-large-language-model-a","title":"Is your multimodal large language model a good science tutor?","date":"2025-05-09","arxiv_id":"2505.06418","repositories_listed":0,"syntology":null},{"url":null,"slug":"monetgpt-solving-puzzles-enhances-mllms-image","title":"MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills","date":"2025-05-09","arxiv_id":"2505.06176","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-path-to-multimodal-generalist-general","title":"On Path to Multimodal Generalist: General-Level and General-Bench","date":"2025-05-07","arxiv_id":"2505.04620","repositories_listed":0,"syntology":null},{"url":null,"slug":"timesoccer-an-end-to-end-multimodal-large","title":"TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation","date":"2025-04-24","arxiv_id":"2504.17365","repositories_listed":0,"syntology":null},{"url":null,"slug":"faceinsight-a-multimodal-large-language-model","title":"FaceInsight: A Multimodal Large Language Model for Face Perception","date":"2025-04-22","arxiv_id":"2504.15624","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatexaonepath-an-expert-level-multimodal","title":"ChatEXAONEPath: An Expert-level Multimodal Large Language Model for Histopathology Using Whole Slide Images","date":"2025-04-17","arxiv_id":"2504.13023","repositories_listed":0,"syntology":null}],"record_sha256":"39cbb434ca6ec9ad628eaaf80cf0f9ff8a78dca7a32a717550a3fe7eba7d3123","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}