{"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/mme","name":"MME","slug":"mme","description_markdown":"MME is a comprehensive evaluation benchmark for multimodal large language models. It measures both perception and cognition abilities on a total of 14 subtasks, including existence, count, position, color, poster, celebrity, scene, landmark, artwork, OCR, commonsense reasoning, numerical calculation, text translation, and code reasoning.","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":95,"papers_with_code":47,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/multimodal-reasoning","name":"Multimodal Reasoning"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":95,"of":95,"of_with_code":47,"tagged_in_all":95,"counts":{"archive_papers_tagged":95,"with_a_code_link":47,"where_syntology_ran_a_sample":27,"not_listed_spam_title":0,"listed":95,"listed_where_code_ran":27,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":21,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":21,"listed_every_run_a_failure_of_syntologys_instrument":6,"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/semi-supervised-domain-adaptation-via-minimax","slug":"semi-supervised-domain-adaptation-via-minimax","title":"Semi-supervised Domain Adaptation via Minimax Entropy","date":"2019-04-13","arxiv_id":"1904.06487","repositories_listed":5,"syntology":{"n":24,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":14,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 4 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/semi-supervised-domain-adaptation-via-minimax#ran","syntology_url":"https://syntology.ai/paper/1904.06487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06487"}},"official":null}},{"url":"/paper/mme-survey-a-comprehensive-survey-on","slug":"mme-survey-a-comprehensive-survey-on","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","date":"2024-11-22","arxiv_id":"2411.15296","repositories_listed":4,"syntology":null},{"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/internlm-xcomposer-a-vision-language-large","slug":"internlm-xcomposer-a-vision-language-large","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","date":"2023-09-26","arxiv_id":"2309.15112","repositories_listed":3,"syntology":null},{"url":"/paper/videoeval-pro-robust-and-realistic-long-video","slug":"videoeval-pro-robust-and-realistic-long-video","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","date":"2025-05-20","arxiv_id":"2505.14640","repositories_listed":2,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoeval-pro-robust-and-realistic-long-video#ran","syntology_url":"https://syntology.ai/paper/2505.14640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14640"}},"official":null}},{"url":"/paper/timechat-online-80-visual-tokens-are","slug":"timechat-online-80-visual-tokens-are","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","date":"2025-04-24","arxiv_id":"2504.17343","repositories_listed":2,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/timechat-online-80-visual-tokens-are#ran","syntology_url":"https://syntology.ai/paper/2504.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.17343"}},"official":{"repos":["yaolinli/TimeChat-Online"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["listed"]}}},{"url":"/paper/spatial-r1-enhancing-mllms-in-video-spatial","slug":"spatial-r1-enhancing-mllms-in-video-spatial","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","date":"2025-04-02","arxiv_id":"2504.01805","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":2,"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/spatial-r1-enhancing-mllms-in-video-spatial#ran","syntology_url":"https://syntology.ai/paper/2504.01805","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01805"}},"official":{"repos":["ouyangkun10/spacer","ouyangkun10/spatial-r1"],"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/long-context-transfer-from-language-to-vision","slug":"long-context-transfer-from-language-to-vision","title":"Long Context Transfer from Language to Vision","date":"2024-06-24","arxiv_id":"2406.16852","repositories_listed":2,"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/long-context-transfer-from-language-to-vision#ran","syntology_url":"https://syntology.ai/paper/2406.16852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16852"}},"official":{"repos":["evolvinglmms-lab/longva"],"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":["listed","official","unlocated"]}}},{"url":"/paper/mitigating-hallucinations-in-large-vision","slug":"mitigating-hallucinations-in-large-vision","title":"Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding","date":"2024-03-27","arxiv_id":"2403.18715","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/mitigating-hallucinations-in-large-vision#ran","syntology_url":"https://syntology.ai/paper/2403.18715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.18715"}},"official":{"repos":["p1k0pan/ICD"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/a-challenger-to-gpt-4v-early-explorations-of","slug":"a-challenger-to-gpt-4v-early-explorations-of","title":"A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise","date":"2023-12-19","arxiv_id":"2312.12436","repositories_listed":2,"syntology":null},{"url":"/paper/mmicl-empowering-vision-language-model-with","slug":"mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","date":"2023-09-14","arxiv_id":"2309.07915","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mmicl-empowering-vision-language-model-with#ran","syntology_url":"https://syntology.ai/paper/2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}},"official":{"repos":["haozhezhao/mic","pkunlp-icler/mic"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/m-3-video-masked-motion-modeling-for-self","slug":"m-3-video-masked-motion-modeling-for-self","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","date":"2022-10-12","arxiv_id":"2210.06096","repositories_listed":2,"syntology":null},{"url":"/paper/high-resolution-visual-reasoning-via-multi","slug":"high-resolution-visual-reasoning-via-multi","title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","date":"2025-07-08","arxiv_id":"2507.05920","repositories_listed":1,"syntology":null},{"url":"/paper/flash-vstream-efficient-real-time","slug":"flash-vstream-efficient-real-time","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","date":"2025-06-30","arxiv_id":"2506.23825","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/flash-vstream-efficient-real-time#ran","syntology_url":"https://syntology.ai/paper/2506.23825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.23825"}},"official":{"repos":["IVGSZ/Flash-VStream"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/videodeepresearch-long-video-understanding","slug":"videodeepresearch-long-video-understanding","title":"VideoDeepResearch: Long Video Understanding With Agentic Tool Using","date":"2025-06-12","arxiv_id":"2506.10821","repositories_listed":1,"syntology":null},{"url":"/paper/silvr-a-simple-language-based-video-reasoning","slug":"silvr-a-simple-language-based-video-reasoning","title":"SiLVR: A Simple Language-based Video Reasoning Framework","date":"2025-05-30","arxiv_id":"2505.24869","repositories_listed":1,"syntology":null},{"url":"/paper/frag-frame-selection-augmented-generation-for","slug":"frag-frame-selection-augmented-generation-for","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","date":"2025-04-24","arxiv_id":"2504.17447","repositories_listed":1,"syntology":null},{"url":"/paper/eagle-2-5-boosting-long-context-post-training","slug":"eagle-2-5-boosting-long-context-post-training","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","date":"2025-04-21","arxiv_id":"2504.15271","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":2,"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/eagle-2-5-boosting-long-context-post-training#ran","syntology_url":"https://syntology.ai/paper/2504.15271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.15271"}},"official":null}},{"url":"/paper/bolt-boost-large-vision-language-model","slug":"bolt-boost-large-vision-language-model","title":"BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding","date":"2025-03-27","arxiv_id":"2503.21483","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":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) · 0 unverified","sample_list":"/paper/bolt-boost-large-vision-language-model#ran","syntology_url":"https://syntology.ai/paper/2503.21483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21483"}},"official":{"repos":["sming256/bolt"],"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/instruction-aligned-visual-attention-for","slug":"instruction-aligned-visual-attention-for","title":"Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models","date":"2025-03-24","arxiv_id":"2503.18556","repositories_listed":1,"syntology":null},{"url":"/paper/quota-query-oriented-token-assignment-via-cot","slug":"quota-query-oriented-token-assignment-via-cot","title":"QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension","date":"2025-03-11","arxiv_id":"2503.08689","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/quota-query-oriented-token-assignment-via-cot#ran","syntology_url":"https://syntology.ai/paper/2503.08689","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08689"}},"official":{"repos":["mac-automl/quota"],"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/re-imagining-multimodal-instruction-tuning-a","slug":"re-imagining-multimodal-instruction-tuning-a","title":"Re-Imagining Multimodal Instruction Tuning: A Representation View","date":"2025-03-02","arxiv_id":"2503.00723","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/re-imagining-multimodal-instruction-tuning-a#ran","syntology_url":"https://syntology.ai/paper/2503.00723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00723"}},"official":{"repos":["comeandcode/MRT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"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/expand-vsr-benchmark-for-vllm-to-expertize-in","slug":"expand-vsr-benchmark-for-vllm-to-expertize-in","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","date":"2024-12-24","arxiv_id":"2412.18224","repositories_listed":1,"syntology":null},{"url":"/paper/lyra-an-efficient-and-speech-centric","slug":"lyra-an-efficient-and-speech-centric","title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","date":"2024-12-12","arxiv_id":"2412.09501","repositories_listed":1,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/lyra-an-efficient-and-speech-centric#ran","syntology_url":"https://syntology.ai/paper/2412.09501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09501"}},"official":{"repos":["dvlab-research/Lyra"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/video-rag-visually-aligned-retrieval","slug":"video-rag-visually-aligned-retrieval","title":"Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension","date":"2024-11-20","arxiv_id":"2411.13093","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-rag-visually-aligned-retrieval#ran","syntology_url":"https://syntology.ai/paper/2411.13093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13093"}},"official":{"repos":["leon1207/video-rag-master"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/dynamic-multimodal-evaluation-with-flexible","slug":"dynamic-multimodal-evaluation-with-flexible","title":"Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping","date":"2024-10-11","arxiv_id":"2410.08695","repositories_listed":1,"syntology":null},{"url":"/paper/to-preserve-or-to-compress-an-in-depth-study","slug":"to-preserve-or-to-compress-an-in-depth-study","title":"To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models","date":"2024-10-09","arxiv_id":"2410.06765","repositories_listed":1,"syntology":null},{"url":"/paper/mitigating-modality-prior-induced","slug":"mitigating-modality-prior-induced","title":"Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality","date":"2024-10-07","arxiv_id":"2410.04780","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mitigating-modality-prior-induced#ran","syntology_url":"https://syntology.ai/paper/2410.04780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04780"}},"official":{"repos":["the-martyr/causalmm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tubench-benchmarking-large-vision-language","slug":"tubench-benchmarking-large-vision-language","title":"TUBench: Benchmarking Large Vision-Language Models on Trustworthiness with Unanswerable Questions","date":"2024-10-05","arxiv_id":"2410.04107","repositories_listed":1,"syntology":null},{"url":"/paper/pargo-bridging-vision-language-with-partial","slug":"pargo-bridging-vision-language-with-partial","title":"ParGo: Bridging Vision-Language with Partial and Global Views","date":"2024-08-23","arxiv_id":"2408.12928","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pargo-bridging-vision-language-with-partial#ran","syntology_url":"https://syntology.ai/paper/2408.12928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12928"}},"official":{"repos":["bytedance/pargo"],"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/l4dr-lidar-4dradar-fusion-for-weather-robust","slug":"l4dr-lidar-4dradar-fusion-for-weather-robust","title":"L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection","date":"2024-08-07","arxiv_id":"2408.03677","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/l4dr-lidar-4dradar-fusion-for-weather-robust#ran","syntology_url":"https://syntology.ai/paper/2408.03677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03677"}},"official":{"repos":["ylwhxht/l4dr"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/decoding-multilingual-moral-preferences","slug":"decoding-multilingual-moral-preferences","title":"Decoding Multilingual Moral Preferences: Unveiling LLM's Biases Through the Moral Machine Experiment","date":"2024-07-21","arxiv_id":"2407.15184","repositories_listed":1,"syntology":null},{"url":"/paper/video-mme-the-first-ever-comprehensive","slug":"video-mme-the-first-ever-comprehensive","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","date":"2024-05-31","arxiv_id":"2405.21075","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/video-mme-the-first-ever-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2405.21075","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.21075"}},"official":null}},{"url":"/paper/videotree-adaptive-tree-based-video","slug":"videotree-adaptive-tree-based-video","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","date":"2024-05-29","arxiv_id":"2405.19209","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videotree-adaptive-tree-based-video#ran","syntology_url":"https://syntology.ai/paper/2405.19209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19209"}},"official":{"repos":["Ziyang412/VideoTree"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/joint-visual-and-text-prompting-for-improved","slug":"joint-visual-and-text-prompting-for-improved","title":"Joint Visual and Text Prompting for Improved Object-Centric Perception with Multimodal Large Language Models","date":"2024-04-06","arxiv_id":"2404.04514","repositories_listed":1,"syntology":null},{"url":"/paper/pensieve-retrospect-then-compare-mitigates","slug":"pensieve-retrospect-then-compare-mitigates","title":"Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination","date":"2024-03-21","arxiv_id":"2403.14401","repositories_listed":1,"syntology":null},{"url":"/paper/hyperllava-dynamic-visual-and-language-expert","slug":"hyperllava-dynamic-visual-and-language-expert","title":"HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models","date":"2024-03-20","arxiv_id":"2403.13447","repositories_listed":1,"syntology":null},{"url":"/paper/honeybee-locality-enhanced-projector-for","slug":"honeybee-locality-enhanced-projector-for","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","date":"2023-12-11","arxiv_id":"2312.06742","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/honeybee-locality-enhanced-projector-for#ran","syntology_url":"https://syntology.ai/paper/2312.06742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06742"}},"official":{"repos":["kakaobrain/honeybee"],"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/prompt-highlighter-interactive-control-for","slug":"prompt-highlighter-interactive-control-for","title":"Prompt Highlighter: Interactive Control for Multi-Modal LLMs","date":"2023-12-07","arxiv_id":"2312.04302","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prompt-highlighter-interactive-control-for#ran","syntology_url":"https://syntology.ai/paper/2312.04302","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04302"}},"official":{"repos":["dvlab-research/prompt-highlighter"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/beyond-hallucinations-enhancing-lvlms-through","slug":"beyond-hallucinations-enhancing-lvlms-through","title":"Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization","date":"2023-11-28","arxiv_id":"2311.16839","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":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) · 1 unverified","sample_list":"/paper/beyond-hallucinations-enhancing-lvlms-through#ran","syntology_url":"https://syntology.ai/paper/2311.16839","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16839"}},"official":{"repos":["opendatalab/ha-dpo"],"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/sharegpt4v-improving-large-multi-modal-models","slug":"sharegpt4v-improving-large-multi-modal-models","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","date":"2023-11-21","arxiv_id":"2311.12793","repositories_listed":1,"syntology":null},{"url":"/paper/what-makes-for-good-visual-instructions","slug":"what-makes-for-good-visual-instructions","title":"What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning","date":"2023-11-02","arxiv_id":"2311.01487","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":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/what-makes-for-good-visual-instructions#ran","syntology_url":"https://syntology.ai/paper/2311.01487","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.01487"}},"official":{"repos":["rucaibox/comvint"],"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/bliva-a-simple-multimodal-llm-for-better","slug":"bliva-a-simple-multimodal-llm-for-better","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","date":"2023-08-19","arxiv_id":"2308.09936","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/bliva-a-simple-multimodal-llm-for-better#ran","syntology_url":"https://syntology.ai/paper/2308.09936","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09936"}},"official":{"repos":["mlpc-ucsd/bliva"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/empowering-vision-language-models-to-follow","slug":"empowering-vision-language-models-to-follow","title":"Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions","date":"2023-08-08","arxiv_id":"2308.04152","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"10 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; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/empowering-vision-language-models-to-follow#ran","syntology_url":"https://syntology.ai/paper/2308.04152","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04152"}},"official":{"repos":["dcdmllm/cheetah"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/maal-multimodality-aware-autoencoder-based","slug":"maal-multimodality-aware-autoencoder-based","title":"MAAL: Multimodality-Aware Autoencoder-Based Affordance Learning for 3D Articulated Objects","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mm-gnn-mix-moment-graph-neural-network","slug":"mm-gnn-mix-moment-graph-neural-network","title":"MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution","date":"2022-08-15","arxiv_id":"2208.07012","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 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; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mm-gnn-mix-moment-graph-neural-network#ran","syntology_url":"https://syntology.ai/paper/2208.07012","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07012"}},"official":{"repos":["wendongbi/MMGNN"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":null,"slug":"q-frame-query-aware-frame-selection-and-multi","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","date":"2025-06-27","arxiv_id":"2506.22139","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-vision-planner-and-executor-for-text","title":"Language-Vision Planner and Executor for Text-to-Visual Reasoning","date":"2025-06-09","arxiv_id":"2506.07778","repositories_listed":0,"syntology":null},{"url":null,"slug":"dyntok-dynamic-compression-of-visual-tokens","title":"DynTok: Dynamic Compression of Visual Tokens for Efficient and Effective Video Understanding","date":"2025-06-04","arxiv_id":"2506.03990","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-or-slow-integrating-fast-intuition-and","title":"Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering","date":"2025-06-01","arxiv_id":"2506.00806","repositories_listed":0,"syntology":null},{"url":null,"slug":"evomoe-expert-evolution-in-mixture-of-experts","title":"EvoMoE: Expert Evolution in Mixture of Experts for Multimodal Large Language Models","date":"2025-05-28","arxiv_id":"2505.23830","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-reasoning-a-comprehensive-benchmark-for","title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","date":"2025-05-27","arxiv_id":"2505.21327","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-visual-reliance-in-text-generation","title":"Enhancing Visual Reliance in Text Generation: A Bayesian Perspective on Mitigating Hallucination in Large Vision-Language Models","date":"2025-05-26","arxiv_id":"2505.19498","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-via-inter-layer","title":"Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models","date":"2025-05-18","arxiv_id":"2505.12343","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10917","title":"VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization","date":"2025-05-16","arxiv_id":"2505.10917","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-instruction-tuning-with-chain-of","title":"Visual Instruction Tuning with Chain of Region-of-Interest","date":"2025-05-11","arxiv_id":"2505.06840","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-lmm-for-efficient-video-understanding-via","title":"An LMM for Efficient Video Understanding via Reinforced Compression of Video Cubes","date":"2025-04-21","arxiv_id":"2504.15270","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-unify-a-comprehensive-benchmark-for","title":"MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models","date":"2025-04-04","arxiv_id":"2504.03641","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-llm-video-understanding-with-16","title":"Improving LLM Video Understanding with 16 Frames Per Second","date":"2025-03-18","arxiv_id":"2503.13956","repositories_listed":0,"syntology":null},{"url":null,"slug":"logic-in-frames-dynamic-keyframe-search-via","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","date":"2025-03-17","arxiv_id":"2503.13139","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-high-frequency-harmony-mmwave-radar-and","title":"Ultra-High-Frequency Harmony: mmWave Radar and Event Camera Orchestrate Accurate Drone Landing","date":"2025-02-20","arxiv_id":"2502.14992","repositories_listed":0,"syntology":null},{"url":null,"slug":"aide-agentically-improve-visual-language","title":"AIDE: Agentically Improve Visual Language Model with Domain Experts","date":"2025-02-13","arxiv_id":"2502.09051","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-cot-benchmarking-chain-of-thought-in","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","date":"2025-02-13","arxiv_id":"2502.09621","repositories_listed":0,"syntology":null},{"url":null,"slug":"hummingbird-high-fidelity-image-generation","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","date":"2025-02-07","arxiv_id":"2502.05153","repositories_listed":0,"syntology":null},{"url":null,"slug":"mitigating-hallucinations-in-large-vision-5","title":"Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding","date":"2025-02-03","arxiv_id":"2502.01056","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-industry-a-cross-industry-multimodal","title":"MME-Industry: A Cross-Industry Multimodal Evaluation Benchmark","date":"2025-01-28","arxiv_id":"2501.16688","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-preference-optimization-for-long","title":"Temporal Preference Optimization for Long-Form Video Understanding","date":"2025-01-23","arxiv_id":"2501.13919","repositories_listed":0,"syntology":null},{"url":null,"slug":"gformer-accelerating-large-language-models","title":"GFormer: Accelerating Large Language Models with Optimized Transformers on Gaudi Processors","date":"2024-12-19","arxiv_id":"2412.19829","repositories_listed":0,"syntology":null},{"url":null,"slug":"apollo-an-exploration-of-video-understanding","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","date":"2024-12-13","arxiv_id":"2412.10360","repositories_listed":0,"syntology":null},{"url":null,"slug":"eaco-enhancing-alignment-in-multimodal-llms","title":"EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation","date":"2024-12-06","arxiv_id":"2412.04903","repositories_listed":0,"syntology":null},{"url":null,"slug":"orthus-autoregressive-interleaved-image-text","title":"Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads","date":"2024-11-28","arxiv_id":"2412.00127","repositories_listed":0,"syntology":null},{"url":null,"slug":"saven-vid-synergistic-audio-visual","title":"SAVEn-Vid: Synergistic Audio-Visual Integration for Enhanced Understanding in Long Video Context","date":"2024-11-25","arxiv_id":"2411.16213","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-instruction-following-capability-of","title":"Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy","date":"2024-11-23","arxiv_id":"2411.15453","repositories_listed":0,"syntology":null},{"url":null,"slug":"economic-evaluation-of-empowering-older","title":"The economic value of empowering older patients transitioning from hospital to home: Evidence from the 'Your Care Needs You' intervention","date":"2024-11-07","arxiv_id":"2411.04339","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-finance-a-multimodal-finance-benchmark","title":"MME-Finance: A Multimodal Finance Benchmark for Expert-level Understanding and Reasoning","date":"2024-11-05","arxiv_id":"2411.03314","repositories_listed":0,"syntology":null},{"url":null,"slug":"zipvl-efficient-large-vision-language-models","title":"ZipVL: Efficient Large Vision-Language Models with Dynamic Token Sparsification","date":"2024-10-11","arxiv_id":"2410.08584","repositories_listed":0,"syntology":null},{"url":null,"slug":"temporal-reasoning-transfer-from-text-to","title":"Temporal Reasoning Transfer from Text to Video","date":"2024-10-08","arxiv_id":"2410.06166","repositories_listed":0,"syntology":null},{"url":null,"slug":"damro-dive-into-the-attention-mechanism-of","title":"DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination","date":"2024-10-06","arxiv_id":"2410.04514","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-realworld-could-your-multimodal-llm","title":"MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?","date":"2024-08-23","arxiv_id":"2408.13257","repositories_listed":0,"syntology":null},{"url":null,"slug":"drvideo-document-retrieval-based-long-video","title":"DrVideo: Document Retrieval Based Long Video Understanding","date":"2024-06-18","arxiv_id":"2406.12846","repositories_listed":0,"syntology":null},{"url":null,"slug":"don-t-miss-the-forest-for-the-trees","title":"Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models","date":"2024-05-28","arxiv_id":"2405.17820","repositories_listed":0,"syntology":null},{"url":null,"slug":"ritual-random-image-transformations-as-a","title":"RITUAL: Random Image Transformations as a Universal Anti-hallucination Lever in Large Vision Language Models","date":"2024-05-28","arxiv_id":"2405.17821","repositories_listed":0,"syntology":null},{"url":"/paper/silkie-preference-distillation-for-large","slug":"silkie-preference-distillation-for-large","title":"Silkie: Preference Distillation for Large Visual Language Models","date":"2023-12-17","arxiv_id":"2312.10665","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-use-of-symmetry-for-models-with-variable","title":"The Use of Symmetry for Models with Variable-size Variables","date":"2023-11-15","arxiv_id":"2311.08650","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-the-spatial-awareness-capability-of","title":"Enhancing the Spatial Awareness Capability of Multi-Modal Large Language Model","date":"2023-10-31","arxiv_id":"2310.20357","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-and-in-depth-performance-study","title":"Benchmarking and In-depth Performance Study of Large Language Models on Habana Gaudi Processors","date":"2023-09-29","arxiv_id":"2309.16976","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptation-via-minimax-entropy-for","title":"Domain Adaptation via Minimax Entropy for Real/Bogus Classification of Astronomical Alerts","date":"2023-08-15","arxiv_id":"2308.07538","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-evaluation-approach-for-medical","title":"Multi-Modal Evaluation Approach for Medical Image Segmentation","date":"2023-02-08","arxiv_id":"2302.04135","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-crs-multi-metric-evaluation-based-on","title":"MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue","date":"2022-06-19","arxiv_id":"2206.09403","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-methods-for-inferring-the","title":"Machine Learning Methods for Inferring the Number of UAV Emitters via Massive MIMO Receive Array","date":"2022-03-02","arxiv_id":"2203.00917","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-meta-learning-for-multi-source-and","title":"Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation","date":"2020-04-09","arxiv_id":"2004.04398","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-multilingual-meta-embeddings-for","title":"Learning Multilingual Meta-Embeddings for Code-Switching Named Entity Recognition","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-hybrid-5g-services-in","title":"Deep Learning for Hybrid 5G Services in Mobile Edge Computing Systems: Learn from a Digital Twin","date":"2019-06-30","arxiv_id":"1907.01523","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-k-medoids-via-true-error-bound-and","title":"Scalable K-Medoids via True Error Bound and Familywise Bandits","date":"2019-05-27","arxiv_id":"1905.10979","repositories_listed":0,"syntology":null}],"syntology_records":27,"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":27,"papers_where_code_ran_first_page":"/task/mme/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/mme/papers/ran/1","json":"/task/mme/papers/ran/1.json","rows":27}],"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":"f5764e1468769cc928cb8b68ea4f1b0f92ac91bda568425b37530a02920eaa92","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}