{"id":"https://openalex.org/W7161830371","doi":"https://doi.org/10.48550/arxiv.2605.19506","title":"EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning","display_name":"EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161830371","doi":"https://doi.org/10.48550/arxiv.2605.19506"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19506","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":null,"license_id":null,"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.2605.19506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100438185","display_name":"Pengtao Ma","orcid":"https://orcid.org/0000-0002-0587-8635"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Pengtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136583002","display_name":"Ziliang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Ziliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089189331","display_name":"Ciyu Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Ciyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136528189","display_name":"Haoyang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136564647","display_name":"Kaiyuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kaiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101249251","display_name":"Zihang Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Zihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136559960","display_name":"Wenhua Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Wenhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136569864","display_name":"Chen Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014880925","display_name":"Jingao Xu","orcid":"https://orcid.org/0000-0002-8347-2657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jingao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136574726","display_name":"Xinlei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinlei","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":0.48570001125335693,"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":0.48570001125335693,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.17149999737739563,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.09179999679327011,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6904000043869019},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6263999938964844},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5849999785423279},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5496000051498413},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5174999833106995},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5051000118255615},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.49880000948905945},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4043999910354614}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648000121116638},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6904000043869019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6359999775886536},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6263999938964844},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5174999833106995},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5073999762535095},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5051000118255615},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C2777708103","wikidata":"https://www.wikidata.org/wiki/Q852589","display_name":"Motion blur","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2780624872","wikidata":"https://www.wikidata.org/wiki/Q852453","display_name":"Motion detection","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19506","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.19506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19506","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":null,"license_id":null,"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":{"First-person":[0],"dynamic":[1],"spatial":[2,107,145],"reasoning":[3],"requires":[4],"models":[5],"to":[6,39,55,77,88,96,105],"track":[7],"continuous":[8,73],"motion":[9,42,66,75],"and":[10,43,101,130],"precise":[11],"geometric":[12,44],"structure,":[13],"but":[14],"the":[15,41,58,64,119,138],"quadratic":[16],"attention":[17,108],"cost":[18],"of":[19],"Transformer-based":[20],"Video-LLMs":[21],"makes":[22],"dense":[23],"visual":[24,99,114],"tokens":[25],"computationally":[26],"expensive.":[27],"Existing":[28],"token":[29,79,115],"pruning":[30],"paradigms":[31],"predominantly":[32],"rely":[33],"on":[34],"discrete":[35],"static":[36],"snapshots,":[37],"failing":[38],"preserve":[40],"cues":[45,67],"essential":[46],"for":[47,143],"reasoning.":[48],"We":[49,134],"propose":[50],"Event":[51],"Cascade":[52],"Pruning":[53],"(ECP),":[54],"our":[56],"knowledge":[57],"first":[59,139],"training-free":[60],"framework":[61],"that":[62],"leverages":[63],"high-frequency":[65],"from":[68],"event":[69],"cameras":[70],"as":[71],"a":[72],"event-guided":[74],"prior":[76],"guide":[78],"selection.":[80],"ECP":[81,117,148],"combines":[82],"three":[83],"stages:":[84],"Event-Triggered":[85],"Causal":[86],"Sampling":[87],"anchor":[89],"motion-informative":[90],"keyframes,":[91],"Event-guided":[92],"Motion":[93],"Saliency":[94],"Filtering":[95],"suppress":[97],"event-inactive":[98],"tokens,":[100],"Event-Attention":[102],"Ranking":[103],"Fusion":[104],"calibrate":[106],"with":[109],"motion-salient":[110],"dynamics.":[111],"With":[112],"80%":[113],"reduction,":[116],"outperforms":[118],"full-token":[120,156],"baseline":[121],"(37.62%":[122],"vs.":[123],"36.31%)":[124],"while":[125],"achieving":[126],"1.89x":[127],"inference":[128],"speedup":[129],"52%":[131],"GFLOPs":[132],"reduction.":[133],"further":[135],"introduce":[136],"ESR-Real,":[137],"real-world":[140],"RGB-event":[141],"benchmark":[142],"first-person":[144],"reasoning,":[146],"where":[147],"improves":[149],"accuracy":[150],"by":[151],"2.68":[152],"percentage":[153],"points":[154],"over":[155],"baselines.":[157]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}