{"id":"https://openalex.org/W4416036624","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.451","title":"Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing","display_name":"Language-Guided Temporal Token Pruning for Efficient VideoLLM Processing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036624","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.451"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.451","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.451","pdf_url":"https://aclanthology.org/2025.emnlp-main.451.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.451.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110219924","display_name":"Yogesh Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I154549908","display_name":"Indian Institute of Technology Jodhpur","ror":"https://ror.org/03yacj906","country_code":"IN","type":"education","lineage":["https://openalex.org/I154549908"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Yogesh Kumar","raw_affiliation_strings":["Indian Institute of Technology Jodhpur"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Jodhpur","institution_ids":["https://openalex.org/I154549908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5110219924"],"corresponding_institution_ids":["https://openalex.org/I154549908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35412438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8935","last_page":"8942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3409000039100647,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3409000039100647,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.16539999842643738,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0738999992609024,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.47290000319480896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31520000100135803},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3061999976634979},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.29789999127388},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.28690001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6355999708175659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5569000244140625},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.47290000319480896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.25699999928474426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.451","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.451","pdf_url":"https://aclanthology.org/2025.emnlp-main.451.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.451","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.451","pdf_url":"https://aclanthology.org/2025.emnlp-main.451.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036624.pdf","grobid_xml":"https://content.openalex.org/works/W4416036624.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"struggle":[4],"with":[5,57,91],"long-form":[6],"videos":[7],"due":[8],"to":[9,28],"the":[10,71],"quadratic":[11],"complexity":[12],"of":[13,70,86],"attention":[14],"mechanisms.We":[15],"propose":[16],"Language-Guided":[17],"Temporal":[18],"Token":[19],"Pruning":[20],"(LGTTP),":[21],"which":[22],"leverages":[23],"temporal":[24,93],"cues":[25],"from":[26],"queries":[27,90],"adaptively":[29],"prune":[30],"video":[31,100],"tokens,":[32],"preserving":[33,68],"contextual":[34],"continuity":[35],"while":[36,67],"reducing":[37],"computational":[38],"overhead.Unlike":[39],"uniform":[40],"pruning":[41],"or":[42],"keyframe":[43],"selection,":[44],"LGTTP":[45,75],"retains":[46,84],"higher":[47],"token":[48],"density":[49],"in":[50,65],"temporally":[51],"relevant":[52],"segments.Our":[53],"model-agnostic":[54],"framework":[55],"integrates":[56],"TimeChat":[58],"and":[59,80,95],"LLaVA-Video,":[60],"achieving":[61],"a":[62],"65%":[63],"reduction":[64],"computation":[66],"97-99%":[69],"original":[72],"performance.On":[73],"QVHighlights,":[74],"improves":[76],"HIT@1":[77],"by":[78],"+9.5%,":[79],"on":[81,89],"Charades-STA,":[82],"it":[83],"99.6%":[85],"R@1.It":[87],"excels":[88],"explicit":[92],"markers":[94],"remains":[96],"effective":[97],"across":[98],"general":[99],"understanding":[101],"tasks.":[102]},"counts_by_year":[],"updated_date":"2026-03-10T14:07:55.174380","created_date":"2025-11-08T00:00:00"}