{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/momentor-advancing-video-large-language-model","title":"Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning","arxiv_id":"2402.11435","date":"2024-02-18","proceeding":null,"authors":["Long Qian","Juncheng Li","Yu Wu","Yaobo Ye","Hao Fei","Tat-Seng Chua","Yueting Zhuang","Siliang Tang"],"abstract":"Large Language Models (LLMs) demonstrate remarkable proficiency in comprehending and handling text-based tasks. Many efforts are being made to transfer these attributes to video modality, which are termed Video-LLMs. However, existing Video-LLMs can only capture the coarse-grained semantics and are unable to effectively handle tasks related to comprehension or localization of specific video segments. In light of these challenges, we propose Momentor, a Video-LLM capable of accomplishing fine-grained temporal understanding tasks. To support the training of Momentor, we design an automatic data generation engine to construct Moment-10M, a large-scale video instruction dataset with segment-level instruction data. We train Momentor on Moment-10M, enabling it to perform segment-level reasoning and localization. Zero-shot evaluations on several tasks demonstrate that Momentor excels in fine-grained temporally grounded comprehension and localization.","url_abs":"https://arxiv.org/abs/2402.11435v2","url_pdf":"https://arxiv.org/pdf/2402.11435v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"momentor-advancing-video-large-language-model","repo_url":"https://github.com/dcdmllm/momentor","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.11435","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11435"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/DCDmllm/Momentor","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dcdmllm/momentor","reach":null}],"summary":{"ran_draft_wrong":5,"ran":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":10,"ran":7,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":10,"samples":[{"code_sha256_prefix":"42bced349888b65e","entry":"format_moment","repo":"DCDmllm/Momentor","repo_kind":"official","path":"scripts/convert_data.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/scripts/convert_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42bced349888b65e"}},{"code_sha256_prefix":"a73f017868119480","entry":"MomentorConfig","repo":"dcdmllm/momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/dcdmllm/momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a73f017868119480"}},{"code_sha256_prefix":"14833ed5e5a26848","entry":"format_moments","repo":"DCDmllm/Momentor","repo_kind":"official","path":"scripts/convert_data.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/scripts/convert_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14833ed5e5a26848"}},{"code_sha256_prefix":"6ea1f0396bf55635","entry":"position_transfer","repo":"DCDmllm/Momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ea1f0396bf55635"}},{"code_sha256_prefix":"a4e4ac6bcd26d7b2","entry":"reparam","repo":"DCDmllm/Momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a4e4ac6bcd26d7b2"}},{"code_sha256_prefix":"5178bf90bf5f2127","entry":"token_transfer","repo":"DCDmllm/Momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5178bf90bf5f2127"}},{"code_sha256_prefix":"cb69c6cfbad02885","entry":"variable_transfer","repo":"DCDmllm/Momentor","repo_kind":"official","path":"scripts/convert_data.py","file_url":"https://github.com/DCDmllm/Momentor/blob/HEAD/scripts/convert_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb69c6cfbad02885"}},{"code_sha256_prefix":"9f3f28884a65eb13","entry":"MomentorLlamaForCausalLM","repo":"dcdmllm/momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/dcdmllm/momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f3f28884a65eb13"}},{"code_sha256_prefix":"02892a1ac0e45d6d","entry":"MomentorLlamaModel","repo":"dcdmllm/momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/dcdmllm/momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02892a1ac0e45d6d"}},{"code_sha256_prefix":"0acc19d7d8792d3d","entry":"VisionConfig","repo":"dcdmllm/momentor","repo_kind":"official","path":"momentor/model/momentor.py","file_url":"https://github.com/dcdmllm/momentor/blob/HEAD/momentor/model/momentor.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0acc19d7d8792d3d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}