{"id":"https://openalex.org/W7162144075","doi":"https://doi.org/10.48550/arxiv.2605.22078","title":"Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding","display_name":"Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162144075","doi":"https://doi.org/10.48550/arxiv.2605.22078"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.22078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136762382","display_name":"Bingjun Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Bingjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136770560","display_name":"Tony Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tony","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136744588","display_name":"Hanqi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hanqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136778883","display_name":"Xinpeng Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Xinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.914900004863739,"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":0.914900004863739,"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":0.047200001776218414,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01140000019222498,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pooling","display_name":"Pooling","score":0.7283999919891357},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6754999756813049},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.526199996471405},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.4763999879360199},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4187000095844269},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3506999909877777},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.349700003862381},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.34929999709129333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8263999819755554},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7283999919891357},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6754999756813049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289000272750854},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.526199996471405},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.4763999879360199},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3084000051021576},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.305400013923645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26409998536109924}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22078","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,17,136],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"have":[8],"significantly":[9],"advanced":[10],"video":[11],"understanding":[12],"tasks,":[13],"yet":[14],"challenges":[15],"remain":[16],"efficiently":[18],"compressing":[19],"visual":[20,44,56,89,129],"tokens":[21],"while":[22],"preserving":[23],"spatiotemporal":[24,75],"interactions.":[25],"Existing":[26],"methods,":[27],"such":[28],"as":[29],"LLaVA":[30],"family,":[31],"utilize":[32],"simplistic":[33],"pooling":[34],"or":[35],"interpolation":[36],"techniques":[37],"that":[38,107],"overlook":[39],"the":[40,93],"intricate":[41],"dynamics":[42],"of":[43,112],"tokens.":[45],"To":[46],"bridge":[47],"this":[48],"gap,":[49],"we":[50],"propose":[51],"ST-GridPool,":[52],"a":[53],"novel":[54],"training-free":[55],"token":[57,96,130],"enhancement":[58],"method":[59,120],"designed":[60],"specifically":[61],"for":[62,127],"Video":[63,113],"LLMs.":[64],"Our":[65,119,132],"approach":[66],"integrates":[67],"Pyramid":[68],"Temporal":[69],"Gridding":[70],"(PTG),":[71],"which":[72,86],"captures":[73],"multi-grained":[74],"interactions":[76],"through":[77],"hierarchical":[78],"temporal":[79],"gridding,":[80],"and":[81,98,124],"Norm-based":[82],"Spatial":[83],"Pooling":[84],"(NSP),":[85],"preserves":[87],"high-information":[88],"regions":[90],"by":[91],"leveraging":[92],"correlation":[94],"between":[95],"norms":[97],"semantic":[99],"richness.":[100],"Extensive":[101],"experiments":[102],"on":[103],"various":[104],"benchmarks":[105],"demonstrate":[106],"ST-GridPool":[108],"consistently":[109],"enhances":[110],"performance":[111],"LLMs":[114],"without":[115],"requiring":[116],"costly":[117],"retraining.":[118],"offers":[121],"an":[122],"efficient":[123],"plug-and-play":[125],"solution":[126],"improving":[128],"representations.":[131],"code":[133],"is":[134],"available":[135],"https://github.com/bingjunluo/ST-GridPool.":[137]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}