{"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","name":"Multimodal Large Language Model","slug":"multimodal-large-language-model","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":347,"papers_with_code":160,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/offensive-memes-in-singapore-context","name":"Offensive Memes in Singapore Context","full_name":"Offensive Memes in Singapore Context","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":4,"rows_per_page":100,"shown":100,"of":347,"of_with_code":160,"tagged_in_all":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":49,"every_run_a_failure_of_syntologys_instrument":10,"listed_with_a_run_with_no_instrument_failure":49,"listed_every_run_a_failure_of_syntologys_instrument":10,"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/mme-a-comprehensive-evaluation-benchmark-for","slug":"mme-a-comprehensive-evaluation-benchmark-for","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","date":"2023-06-23","arxiv_id":"2306.13394","repositories_listed":4,"syntology":null},{"url":"/paper/shapellm-universal-3d-object-understanding","slug":"shapellm-universal-3d-object-understanding","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","date":"2024-02-27","arxiv_id":"2402.17766","repositories_listed":3,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/shapellm-universal-3d-object-understanding#ran","syntology_url":"https://syntology.ai/paper/2402.17766","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.17766"}},"official":{"repos":["qizekun/ShapeLLM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vargpt-unified-understanding-and-generation","slug":"vargpt-unified-understanding-and-generation","title":"VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model","date":"2025-01-21","arxiv_id":"2501.12327","repositories_listed":2,"syntology":null},{"url":"/paper/remote-sensing-temporal-vision-language","slug":"remote-sensing-temporal-vision-language","title":"Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey","date":"2024-12-03","arxiv_id":"2412.02573","repositories_listed":2,"syntology":null},{"url":"/paper/learn-from-downstream-and-be-yourself-in","slug":"learn-from-downstream-and-be-yourself-in","title":"Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning","date":"2024-11-17","arxiv_id":"2411.10928","repositories_listed":2,"syntology":null},{"url":"/paper/baichuan-omni-technical-report","slug":"baichuan-omni-technical-report","title":"Baichuan-Omni Technical Report","date":"2024-10-11","arxiv_id":"2410.08565","repositories_listed":2,"syntology":null},{"url":"/paper/ovis-structural-embedding-alignment-for","slug":"ovis-structural-embedding-alignment-for","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","date":"2024-05-31","arxiv_id":"2405.20797","repositories_listed":2,"syntology":null},{"url":"/paper/minigpt4-video-advancing-multimodal-llms-for","slug":"minigpt4-video-advancing-multimodal-llms-for","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","date":"2024-04-04","arxiv_id":"2404.03413","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/minigpt4-video-advancing-multimodal-llms-for#ran","syntology_url":"https://syntology.ai/paper/2404.03413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03413"}},"official":{"repos":["Vision-CAIR/MiniGPT4-video"],"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/jailbreaking-attack-against-multimodal-large","slug":"jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","arxiv_id":"2402.02309","repositories_listed":2,"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":3,"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/jailbreaking-attack-against-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2402.02309","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02309"}},"official":{"repos":["abc03570128/jailbreaking-attack-against-multimodal-large-language-model"],"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":["listed","official"]}}},{"url":"/paper/tool-lmm-a-large-multi-modal-model-for-tool","slug":"tool-lmm-a-large-multi-modal-model-for-tool","title":"MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning","date":"2024-01-19","arxiv_id":"2401.10727","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tool-lmm-a-large-multi-modal-model-for-tool#ran","syntology_url":"https://syntology.ai/paper/2401.10727","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.10727"}},"official":{"repos":["mllm-tool/mllm-tool","tool-lmm/tool-lmm"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/timechat-a-time-sensitive-multimodal-large","slug":"timechat-a-time-sensitive-multimodal-large","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","date":"2023-12-04","arxiv_id":"2312.02051","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/timechat-a-time-sensitive-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2312.02051","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02051"}},"official":{"repos":["renshuhuai-andy/timechat"],"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/ferret-refer-and-ground-anything-anywhere-at","slug":"ferret-refer-and-ground-anything-anywhere-at","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","date":"2023-10-11","arxiv_id":"2310.07704","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"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) · 1 unverified","sample_list":"/paper/ferret-refer-and-ground-anything-anywhere-at#ran","syntology_url":"https://syntology.ai/paper/2310.07704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07704"}},"official":{"repos":["apple/ml-ferret"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"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/mfgdiffusion-mask-guided-smoke-synthesis-for","slug":"mfgdiffusion-mask-guided-smoke-synthesis-for","title":"MFGDiffusion: Mask-Guided Smoke Synthesis for Enhanced Forest Fire Detection","date":"2025-07-15","arxiv_id":"2507.11252","repositories_listed":1,"syntology":null},{"url":"/paper/oraclefusion-assisting-the-decipherment-of","slug":"oraclefusion-assisting-the-decipherment-of","title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","date":"2025-06-26","arxiv_id":"2506.21101","repositories_listed":1,"syntology":null},{"url":"/paper/thinksound-chain-of-thought-reasoning-in","slug":"thinksound-chain-of-thought-reasoning-in","title":"ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and Editing","date":"2025-06-26","arxiv_id":"2506.21448","repositories_listed":1,"syntology":null},{"url":"/paper/medtvt-r1-a-multimodal-llm-empowering-medical","slug":"medtvt-r1-a-multimodal-llm-empowering-medical","title":"MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis","date":"2025-06-23","arxiv_id":"2506.18512","repositories_listed":1,"syntology":null},{"url":"/paper/sharegpt-4o-image-aligning-multimodal-models","slug":"sharegpt-4o-image-aligning-multimodal-models","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","date":"2025-06-22","arxiv_id":"2506.18095","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sharegpt-4o-image-aligning-multimodal-models#ran","syntology_url":"https://syntology.ai/paper/2506.18095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18095"}},"official":{"repos":["freedomintelligence/sharegpt-4o-image"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/the-condition-number-as-a-scale-invariant","slug":"the-condition-number-as-a-scale-invariant","title":"The Condition Number as a Scale-Invariant Proxy for Information Encoding in Neural Units","date":"2025-06-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vis-shepherd-constructing-critic-for-llm","slug":"vis-shepherd-constructing-critic-for-llm","title":"VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation","date":"2025-06-16","arxiv_id":"2506.13326","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"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) · 0 unverified","sample_list":"/paper/vis-shepherd-constructing-critic-for-llm#ran","syntology_url":"https://syntology.ai/paper/2506.13326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13326"}},"official":{"repos":["bopan3/vis-shepherd"],"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":["official"]}}},{"url":"/paper/period-llm-extending-the-periodic-capability","slug":"period-llm-extending-the-periodic-capability","title":"Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model","date":"2025-05-30","arxiv_id":"2505.24476","repositories_listed":1,"syntology":null},{"url":"/paper/un-2-clip-improving-clip-s-visual-detail","slug":"un-2-clip-improving-clip-s-visual-detail","title":"un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP","date":"2025-05-30","arxiv_id":"2505.24517","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-rag-sub-dimensional-retrieval","slug":"cross-modal-rag-sub-dimensional-retrieval","title":"Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation","date":"2025-05-28","arxiv_id":"2505.21956","repositories_listed":1,"syntology":null},{"url":"/paper/geollava-8k-scaling-remote-sensing-multimodal","slug":"geollava-8k-scaling-remote-sensing-multimodal","title":"GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution","date":"2025-05-27","arxiv_id":"2505.21375","repositories_listed":1,"syntology":null},{"url":"/paper/diagnosing-and-mitigating-modality","slug":"diagnosing-and-mitigating-modality","title":"Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models","date":"2025-05-26","arxiv_id":"2505.19616","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":3,"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/diagnosing-and-mitigating-modality#ran","syntology_url":"https://syntology.ai/paper/2505.19616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19616"}},"official":null}},{"url":"/paper/multimodal-llm-guided-semantic-correction-in","slug":"multimodal-llm-guided-semantic-correction-in","title":"Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion","date":"2025-05-26","arxiv_id":"2505.20053","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-multimodal-large-language-model","slug":"unifying-multimodal-large-language-model","title":"Unifying Multimodal Large Language Model Capabilities and Modalities via Model Merging","date":"2025-05-26","arxiv_id":"2505.19892","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unifying-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2505.19892","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19892"}},"official":{"repos":["walkerworldpeace/mllmerging"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chemmllm-chemical-multimodal-large-language","slug":"chemmllm-chemical-multimodal-large-language","title":"ChemMLLM: Chemical Multimodal Large Language Model","date":"2025-05-22","arxiv_id":"2505.16326","repositories_listed":1,"syntology":null},{"url":"/paper/dimple-discrete-diffusion-multimodal-large","slug":"dimple-discrete-diffusion-multimodal-large","title":"Dimple: Discrete Diffusion Multimodal Large Language Model with Parallel Decoding","date":"2025-05-22","arxiv_id":"2505.16990","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/dimple-discrete-diffusion-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2505.16990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16990"}},"official":{"repos":["yu-rp/dimple"],"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/web-shepherd-advancing-prms-for-reinforcing","slug":"web-shepherd-advancing-prms-for-reinforcing","title":"Web-Shepherd: Advancing PRMs for Reinforcing Web Agents","date":"2025-05-21","arxiv_id":"2505.15277","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/web-shepherd-advancing-prms-for-reinforcing#ran","syntology_url":"https://syntology.ai/paper/2505.15277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15277"}},"official":{"repos":["kyle8581/Web-Shepherd"],"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/busterx-mllm-powered-ai-generated-video","slug":"busterx-mllm-powered-ai-generated-video","title":"BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation","date":"2025-05-19","arxiv_id":"2505.12620","repositories_listed":1,"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/busterx-mllm-powered-ai-generated-video#ran","syntology_url":"https://syntology.ai/paper/2505.12620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12620"}},"official":{"repos":["l8cv/busterx"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mindomni-unleashing-reasoning-generation-in","slug":"mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","date":"2025-05-19","arxiv_id":"2505.13031","repositories_listed":1,"syntology":null},{"url":"/paper/2505-10769","slug":"2505-10769","title":"Unifying Segment Anything in Microscopy with Multimodal Large Language Model","date":"2025-05-16","arxiv_id":"2505.10769","repositories_listed":1,"syntology":null},{"url":"/paper/batch-augmentation-with-unimodal-fine-tuning","slug":"batch-augmentation-with-unimodal-fine-tuning","title":"Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning","date":"2025-05-10","arxiv_id":"2505.06592","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-aware-fake-videos-detection-on","slug":"consistency-aware-fake-videos-detection-on","title":"Consistency-aware Fake Videos Detection on Short Video Platforms","date":"2025-04-30","arxiv_id":"2504.21495","repositories_listed":1,"syntology":null},{"url":"/paper/smartfreeedit-mask-free-spatial-aware-image","slug":"smartfreeedit-mask-free-spatial-aware-image","title":"SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding","date":"2025-04-17","arxiv_id":"2504.12704","repositories_listed":1,"syntology":null},{"url":"/paper/anomalyr1-a-grpo-based-end-to-end-mllm-for","slug":"anomalyr1-a-grpo-based-end-to-end-mllm-for","title":"AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection","date":"2025-04-16","arxiv_id":"2504.11914","repositories_listed":1,"syntology":null},{"url":"/paper/internvl3-exploring-advanced-training-and","slug":"internvl3-exploring-advanced-training-and","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","date":"2025-04-14","arxiv_id":"2504.10479","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/internvl3-exploring-advanced-training-and#ran","syntology_url":"https://syntology.ai/paper/2504.10479","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10479"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/the-scalability-of-simplicity-empirical","slug":"the-scalability-of-simplicity-empirical","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","date":"2025-04-14","arxiv_id":"2504.10462","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"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) · 7 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/the-scalability-of-simplicity-empirical#ran","syntology_url":"https://syntology.ai/paper/2504.10462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.10462"}},"official":{"repos":["bytedance/sail"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-time-series-forecasting-via-multi","slug":"enhancing-time-series-forecasting-via-multi","title":"Enhancing Time Series Forecasting via Multi-Level Text Alignment with LLMs","date":"2025-04-10","arxiv_id":"2504.07360","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-llms-and-multimodal-large","slug":"distributed-llms-and-multimodal-large","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","date":"2025-03-20","arxiv_id":"2503.16585","repositories_listed":1,"syntology":null},{"url":"/paper/open3dvqa-a-benchmark-for-comprehensive","slug":"open3dvqa-a-benchmark-for-comprehensive","title":"Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space","date":"2025-03-14","arxiv_id":"2503.11094","repositories_listed":1,"syntology":null},{"url":"/paper/got-unleashing-reasoning-capability-of","slug":"got-unleashing-reasoning-capability-of","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","date":"2025-03-13","arxiv_id":"2503.10639","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/got-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2503.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10639"}},"official":{"repos":["rongyaofang/got"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/referring-to-any-person","slug":"referring-to-any-person","title":"Referring to Any Person","date":"2025-03-11","arxiv_id":"2503.08507","repositories_listed":1,"syntology":null},{"url":"/paper/next-token-is-enough-realistic-image-quality","slug":"next-token-is-enough-realistic-image-quality","title":"Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model","date":"2025-03-08","arxiv_id":"2503.06141","repositories_listed":1,"syntology":null},{"url":"/paper/r1-omni-explainable-omni-multimodal-emotion","slug":"r1-omni-explainable-omni-multimodal-emotion","title":"R1-Omni: Explainable Omni-Multimodal Emotion Recognition with Reinforcement Learning","date":"2025-03-07","arxiv_id":"2503.05379","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 3 unverified","sample_list":"/paper/r1-omni-explainable-omni-multimodal-emotion#ran","syntology_url":"https://syntology.ai/paper/2503.05379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.05379"}},"official":null}},{"url":"/paper/keeping-yourself-is-important-in-downstream","slug":"keeping-yourself-is-important-in-downstream","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","date":"2025-03-06","arxiv_id":"2503.04543","repositories_listed":1,"syntology":null},{"url":"/paper/pp-docbee-improving-multimodal-document","slug":"pp-docbee-improving-multimodal-document","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","date":"2025-03-06","arxiv_id":"2503.04065","repositories_listed":1,"syntology":null},{"url":"/paper/towards-general-visual-linguistic-face-1","slug":"towards-general-visual-linguistic-face-1","title":"Towards General Visual-Linguistic Face Forgery Detection(V2)","date":"2025-02-28","arxiv_id":"2502.20698","repositories_listed":1,"syntology":null},{"url":"/paper/asymlora-harmonizing-data-conflicts-and","slug":"asymlora-harmonizing-data-conflicts-and","title":"AsymLoRA: Harmonizing Data Conflicts and Commonalities in MLLMs","date":"2025-02-27","arxiv_id":"2502.20035","repositories_listed":1,"syntology":null},{"url":"/paper/introducing-visual-perception-token-into","slug":"introducing-visual-perception-token-into","title":"Introducing Visual Perception Token into Multimodal Large Language Model","date":"2025-02-24","arxiv_id":"2502.17425","repositories_listed":1,"syntology":null},{"url":"/paper/r1-onevision-an-open-source-multimodal-large","slug":"r1-onevision-an-open-source-multimodal-large","title":"R1-Onevision：An Open-Source Multimodal Large Language Model Capable of Deep Reasoning","date":"2025-02-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/omniparser-v2-structured-points-of-thought","slug":"omniparser-v2-structured-points-of-thought","title":"OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models","date":"2025-02-22","arxiv_id":"2502.16161","repositories_listed":1,"syntology":null},{"url":"/paper/towards-text-image-interleaved-retrieval","slug":"towards-text-image-interleaved-retrieval","title":"Towards Text-Image Interleaved Retrieval","date":"2025-02-18","arxiv_id":"2502.12799","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-text-image-interleaved-retrieval#ran","syntology_url":"https://syntology.ai/paper/2502.12799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12799"}},"official":{"repos":["vec-ai/wikihow-tiir"],"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":["found_in_text"]}}},{"url":"/paper/mme5-improving-multimodal-multilingual","slug":"mme5-improving-multimodal-multilingual","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","date":"2025-02-12","arxiv_id":"2502.08468","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-multimodal-llm-for-inspirational","slug":"leveraging-multimodal-llm-for-inspirational","title":"Leveraging Multimodal LLM for Inspirational User Interface Search","date":"2025-01-29","arxiv_id":"2501.17799","repositories_listed":1,"syntology":null},{"url":"/paper/patentlmm-large-multimodal-model-for","slug":"patentlmm-large-multimodal-model-for","title":"PatentLMM: Large Multimodal Model for Generating Descriptions for Patent Figures","date":"2025-01-25","arxiv_id":"2501.15074","repositories_listed":1,"syntology":null},{"url":"/paper/endochat-grounded-multimodal-large-language","slug":"endochat-grounded-multimodal-large-language","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","date":"2025-01-20","arxiv_id":"2501.11347","repositories_listed":1,"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/endochat-grounded-multimodal-large-language#ran","syntology_url":"https://syntology.ai/paper/2501.11347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.11347"}},"official":{"repos":["gkw0010/endochat"],"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/when-language-and-vision-meet-road-safety","slug":"when-language-and-vision-meet-road-safety","title":"When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis","date":"2025-01-17","arxiv_id":"2501.10604","repositories_listed":1,"syntology":null},{"url":"/paper/3ur-llm-an-end-to-end-multimodal-large","slug":"3ur-llm-an-end-to-end-multimodal-large","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","date":"2025-01-14","arxiv_id":"2501.07819","repositories_listed":1,"syntology":null},{"url":"/paper/llava-st-a-multimodal-large-language-model","slug":"llava-st-a-multimodal-large-language-model","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","date":"2025-01-14","arxiv_id":"2501.08282","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/llava-st-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2501.08282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08282"}},"official":{"repos":["appletea233/llava-st"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/parameter-inverted-image-pyramid-networks-for","slug":"parameter-inverted-image-pyramid-networks-for","title":"Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding","date":"2025-01-14","arxiv_id":"2501.07783","repositories_listed":1,"syntology":null},{"url":"/paper/chartcoder-advancing-multimodal-large","slug":"chartcoder-advancing-multimodal-large","title":"ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation","date":"2025-01-11","arxiv_id":"2501.06598","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/chartcoder-advancing-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2501.06598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.06598"}},"official":{"repos":["thunlp/ChartCoder"],"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/valley2-exploring-multimodal-models-with","slug":"valley2-exploring-multimodal-models-with","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","date":"2025-01-10","arxiv_id":"2501.05901","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/valley2-exploring-multimodal-models-with#ran","syntology_url":"https://syntology.ai/paper/2501.05901","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.05901"}},"official":{"repos":["bytedance/valley"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/notes-guided-mllm-reasoning-enhancing-mllm","slug":"notes-guided-mllm-reasoning-enhancing-mllm","title":"Notes-guided MLLM Reasoning: Enhancing MLLM with Knowledge and Visual Notes for Visual Question Answering","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mllm-sul-multimodal-large-language-model-for","slug":"mllm-sul-multimodal-large-language-model-for","title":"MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios","date":"2024-12-27","arxiv_id":"2412.19406","repositories_listed":1,"syntology":null},{"url":"/paper/minigpt-pancreas-multimodal-large-language","slug":"minigpt-pancreas-multimodal-large-language","title":"MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Classification and Detection","date":"2024-12-20","arxiv_id":"2412.15925","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-hypothetical-summary-for-retrieval","slug":"multimodal-hypothetical-summary-for-retrieval","title":"Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering","date":"2024-12-19","arxiv_id":"2412.14880","repositories_listed":1,"syntology":null},{"url":"/paper/idea-bench-how-far-are-generative-models-from","slug":"idea-bench-how-far-are-generative-models-from","title":"IDEA-Bench: How Far are Generative Models from Professional Designing?","date":"2024-12-16","arxiv_id":"2412.11767","repositories_listed":1,"syntology":null},{"url":"/paper/towards-a-multimodal-large-language-model","slug":"towards-a-multimodal-large-language-model","title":"Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine","date":"2024-12-12","arxiv_id":"2412.09278","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":2,"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/towards-a-multimodal-large-language-model#ran","syntology_url":"https://syntology.ai/paper/2412.09278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09278"}},"official":{"repos":["shawnhuang497/medplib"],"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/llava-spacesgg-visual-instruct-tuning-for","slug":"llava-spacesgg-visual-instruct-tuning-for","title":"LLaVA-SpaceSGG: Visual Instruct Tuning for Open-vocabulary Scene Graph Generation with Enhanced Spatial Relations","date":"2024-12-09","arxiv_id":"2412.06322","repositories_listed":1,"syntology":null},{"url":"/paper/expanding-performance-boundaries-of-open","slug":"expanding-performance-boundaries-of-open","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","date":"2024-12-06","arxiv_id":"2412.05271","repositories_listed":1,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"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) · 8 unverified","sample_list":"/paper/expanding-performance-boundaries-of-open#ran","syntology_url":"https://syntology.ai/paper/2412.05271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05271"}},"official":{"repos":["opengvlab/internvl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/liquid-language-models-are-scalable-multi","slug":"liquid-language-models-are-scalable-multi","title":"Liquid: Language Models are Scalable Multi-modal Generators","date":"2024-12-05","arxiv_id":"2412.04332","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/liquid-language-models-are-scalable-multi#ran","syntology_url":"https://syntology.ai/paper/2412.04332","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04332"}},"official":{"repos":["foundationvision/liquid"],"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/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/openad-open-world-autonomous-driving","slug":"openad-open-world-autonomous-driving","title":"OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection","date":"2024-11-26","arxiv_id":"2411.17761","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-mllm-embeddings-and-attribute","slug":"leveraging-mllm-embeddings-and-attribute","title":"Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning","date":"2024-11-18","arxiv_id":"2411.12584","repositories_listed":1,"syntology":null},{"url":"/paper/quantifying-preferences-of-vision-language","slug":"quantifying-preferences-of-vision-language","title":"Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts","date":"2024-11-18","arxiv_id":"2411.11479","repositories_listed":1,"syntology":null},{"url":"/paper/multi-stage-vision-token-dropping-towards","slug":"multi-stage-vision-token-dropping-towards","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","date":"2024-11-16","arxiv_id":"2411.10803","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":1,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"8 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-stage-vision-token-dropping-towards#ran","syntology_url":"https://syntology.ai/paper/2411.10803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10803"}},"official":{"repos":["liuting20/mustdrop"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lhrs-bot-nova-improved-multimodal-large","slug":"lhrs-bot-nova-improved-multimodal-large","title":"LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation","date":"2024-11-14","arxiv_id":"2411.09301","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lhrs-bot-nova-improved-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2411.09301","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09301"}},"official":{"repos":["NJU-LHRS/LHRS-Bot"],"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/magicquill-an-intelligent-interactive-image","slug":"magicquill-an-intelligent-interactive-image","title":"MagicQuill: An Intelligent Interactive Image Editing System","date":"2024-11-14","arxiv_id":"2411.09703","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"12 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magicquill-an-intelligent-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2411.09703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.09703"}},"official":{"repos":["ant-research/MagicQuill"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/storyteller-improving-long-video-description","slug":"storyteller-improving-long-video-description","title":"StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification","date":"2024-11-11","arxiv_id":"2411.07076","repositories_listed":1,"syntology":null},{"url":"/paper/protecting-privacy-in-multimodal-large","slug":"protecting-privacy-in-multimodal-large","title":"Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench","date":"2024-10-29","arxiv_id":"2410.22108","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/protecting-privacy-in-multimodal-large#ran","syntology_url":"https://syntology.ai/paper/2410.22108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22108"}},"official":{"repos":["franciscoliu/MLLMU-Bench"],"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/meaning-typed-prompting-a-technique-for","slug":"meaning-typed-prompting-a-technique-for","title":"Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation","date":"2024-10-22","arxiv_id":"2410.18146","repositories_listed":1,"syntology":null},{"url":"/paper/spa-bench-a-comprehensive-benchmark-for","slug":"spa-bench-a-comprehensive-benchmark-for","title":"SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation","date":"2024-10-19","arxiv_id":"2410.15164","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/spa-bench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2410.15164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15164"}},"official":{"repos":["ai-agents-2030/SPA-Bench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/moba-a-two-level-agent-system-for-efficient","slug":"moba-a-two-level-agent-system-for-efficient","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","date":"2024-10-17","arxiv_id":"2410.13757","repositories_listed":1,"syntology":null},{"url":"/paper/automatically-generating-visual-hallucination","slug":"automatically-generating-visual-hallucination","title":"Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models","date":"2024-10-15","arxiv_id":"2410.11242","repositories_listed":1,"syntology":null},{"url":"/paper/hespi-a-pipeline-for-automatically-detecting","slug":"hespi-a-pipeline-for-automatically-detecting","title":"Hespi: A pipeline for automatically detecting information from hebarium specimen sheets","date":"2024-10-11","arxiv_id":"2410.08740","repositories_listed":1,"syntology":null},{"url":"/paper/pdf-wukong-a-large-multimodal-model-for","slug":"pdf-wukong-a-large-multimodal-model-for","title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","date":"2024-10-08","arxiv_id":"2410.05970","repositories_listed":1,"syntology":null},{"url":"/paper/sca-highly-efficient-semantic-consistent","slug":"sca-highly-efficient-semantic-consistent","title":"SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion","date":"2024-10-03","arxiv_id":"2410.02240","repositories_listed":1,"syntology":null},{"url":"/paper/medvilam-a-multimodal-large-language-model","slug":"medvilam-a-multimodal-large-language-model","title":"MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation","date":"2024-09-29","arxiv_id":"2409.19684","repositories_listed":1,"syntology":null},{"url":"/paper/one-token-to-seg-them-all-language-instructed","slug":"one-token-to-seg-them-all-language-instructed","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","date":"2024-09-29","arxiv_id":"2409.19603","repositories_listed":1,"syntology":{"n":16,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":8,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"8 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; 6 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/one-token-to-seg-them-all-language-instructed#ran","syntology_url":"https://syntology.ai/paper/2409.19603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19603"}},"official":{"repos":["showlab/videolisa"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/clip-moe-towards-building-mixture-of-experts","slug":"clip-moe-towards-building-mixture-of-experts","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","date":"2024-09-28","arxiv_id":"2409.19291","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clip-moe-towards-building-mixture-of-experts#ran","syntology_url":"https://syntology.ai/paper/2409.19291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.19291"}},"official":{"repos":["OpenSparseLLMs/CLIP-MoE"],"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/texttoucher-fine-grained-text-to-touch","slug":"texttoucher-fine-grained-text-to-touch","title":"TextToucher: Fine-Grained Text-to-Touch Generation","date":"2024-09-09","arxiv_id":"2409.05427","repositories_listed":1,"syntology":null},{"url":"/paper/adaptvision-dynamic-input-scaling-in-mllms","slug":"adaptvision-dynamic-input-scaling-in-mllms","title":"AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding","date":"2024-08-30","arxiv_id":"2408.16986","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"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, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adaptvision-dynamic-input-scaling-in-mllms#ran","syntology_url":"https://syntology.ai/paper/2408.16986","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16986"}},"official":{"repos":["harrytea/adaptvision"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multimath-bridging-visual-and-mathematical","slug":"multimath-bridging-visual-and-mathematical","title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","date":"2024-08-30","arxiv_id":"2409.00147","repositories_listed":1,"syntology":{"n":18,"n_ran":17,"n_constructed":0,"n_ran_checked":5,"n_instrument":12,"n_unverified":1,"n_honours":0,"n_violates":4,"n_no_contract":1,"n_pointer_only":3,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 12 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multimath-bridging-visual-and-mathematical#ran","syntology_url":"https://syntology.ai/paper/2409.00147","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00147"}},"official":{"repos":["pengshuai-rin/multimath"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/proteingpt-multimodal-llm-for-protein","slug":"proteingpt-multimodal-llm-for-protein","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","date":"2024-08-21","arxiv_id":"2408.11363","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":4,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/proteingpt-multimodal-llm-for-protein#ran","syntology_url":"https://syntology.ai/paper/2408.11363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11363"}},"official":{"repos":["proteingpt/proteingpt"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ffaa-multimodal-large-language-model-based","slug":"ffaa-multimodal-large-language-model-based","title":"FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant","date":"2024-08-19","arxiv_id":"2408.10072","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/ffaa-multimodal-large-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2408.10072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10072"}},"official":{"repos":["thu-huangzc/FFAA"],"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/harnessing-multimodal-large-language-models","slug":"harnessing-multimodal-large-language-models","title":"Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation","date":"2024-08-19","arxiv_id":"2408.09698","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/harnessing-multimodal-large-language-models#ran","syntology_url":"https://syntology.ai/paper/2408.09698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09698"}},"official":{"repos":["yuyangye/mllm-msr"],"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/medtsllm-leveraging-llms-for-multimodal","slug":"medtsllm-leveraging-llms-for-multimodal","title":"MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis","date":"2024-08-14","arxiv_id":"2408.07773","repositories_listed":1,"syntology":null}],"syntology_records":39,"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":59,"papers_where_code_ran_first_page":"/task/multimodal-large-language-model/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/multimodal-large-language-model/papers/2","json":"/task/multimodal-large-language-model/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/multimodal-large-language-model/papers/3","json":"/task/multimodal-large-language-model/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/multimodal-large-language-model/papers/4","json":"/task/multimodal-large-language-model/papers/4.json","rows":47},{"order":"ran","page":1,"of":1,"url":"/task/multimodal-large-language-model/papers/ran/1","json":"/task/multimodal-large-language-model/papers/ran/1.json","rows":59}],"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":"f561809725de77e43a02beb28a9aa652d63ccae6bcdf51a86df7ad1e2a1daf86","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}