{"id":"https://openalex.org/W7168410370","doi":"https://doi.org/10.1145/3805712.3809757","title":"Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding","display_name":"Think with Grounding: Curriculum Reinforced Reasoning with Video Grounding for Long Video Understanding","publication_year":2026,"publication_date":"2026-07-15","ids":{"openalex":"https://openalex.org/W7168410370","doi":"https://doi.org/10.1145/3805712.3809757"},"language":null,"primary_location":{"id":"doi:10.1145/3805712.3809757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809757","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805712.3809757","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140782189","display_name":"Houlun Chen","orcid":"https://orcid.org/0009-0006-7749-7328"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houlun Chen","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-7749-7328","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140788610","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-0351-2939"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0351-2939","affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140918136","display_name":"Guangyao Li","orcid":"https://orcid.org/0000-0002-2179-8555"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyao Li","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2179-8555","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140940583","display_name":"Yuwei Zhou","orcid":"https://orcid.org/0000-0001-9582-7331"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Zhou","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9582-7331","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140915411","display_name":"Yihan Chen","orcid":"https://orcid.org/0009-0001-5389-2095"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihan Chen","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5389-2095","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140823535","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0001-7118-3666"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7118-3666","affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5140824639","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["DCST, BNRist, Tsinghua University, Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2236-9290","affiliations":[{"raw_affiliation_string":"DCST, BNRist, Tsinghua University, Beijing, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"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":"167","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5486999750137329},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.328000009059906},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.29679998755455017}],"concepts":[{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5486999750137329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46320000290870667},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2953000068664551},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2930999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.28029999136924744}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805712.3809757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809757","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805712.3809757","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805712.3809757","pdf_url":null,"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 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2963017553","https://openalex.org/W2964089981","https://openalex.org/W3175859344","https://openalex.org/W4298364821","https://openalex.org/W4387321091","https://openalex.org/W4402702917","https://openalex.org/W4402727142","https://openalex.org/W4402727520","https://openalex.org/W4402754238","https://openalex.org/W4403791888","https://openalex.org/W4404784276","https://openalex.org/W4413144845","https://openalex.org/W4413145061","https://openalex.org/W4413145251","https://openalex.org/W4413145669","https://openalex.org/W4413145687","https://openalex.org/W4413146669","https://openalex.org/W4413146798","https://openalex.org/W4413147303","https://openalex.org/W4413147815","https://openalex.org/W4413155982","https://openalex.org/W4413156662","https://openalex.org/W4413158337","https://openalex.org/W4415798209","https://openalex.org/W4415798317","https://openalex.org/W4415798545","https://openalex.org/W7160077670","https://openalex.org/W7160098964","https://openalex.org/W7160155217","https://openalex.org/W7160155951","https://openalex.org/W7160158216","https://openalex.org/W7160173378","https://openalex.org/W7160182092"],"related_works":[],"abstract_inverted_index":{"Long":[0],"video":[1,29,51,65,94],"understanding":[2],"(LVU)":[3],"is":[4],"challenging":[5],"due":[6,68],"to":[7,21,26,69,96,100,164,174,178,208,251],"rich":[8],"and":[9,161,202,221,242,255],"complicated":[10],"multimodal":[11],"clues":[12,30,59],"in":[13,31,121],"long":[14,32,74],"temporal":[15,71],"range.":[16],"Current":[17],"methods":[18],"adopt":[19],"reasoning":[20,48,134,182],"improve":[22,252],"the":[23,38,43,46,70,146,190,195,234],"model's":[24],"ability":[25],"analyze":[27],"complex":[28,128,180],"videos":[33,170],"via":[34],"text-form":[35],"reasoning.":[36],"However,":[37],"existing":[39],"literature":[40],"suffers":[41],"from":[42],"fact":[44],"that":[45,87,214,224],"text-only":[47],"under":[49,63],"fixed":[50],"context":[52,66],"may":[53],"exacerbate":[54],"hallucinations":[55],"since":[56],"detailed":[57],"crucial":[58],"are":[60],"often":[61],"ignored":[62],"limited":[64],"length":[67],"redundancy":[72],"of":[73,171,186,236],"videos.":[75],"To":[76],"address":[77],"this":[78],"gap,":[79],"we":[80,138,188,206],"propose":[81,189,207],"Video-TwG,":[82],"a":[83,89,122,140,153,210],"curriculum":[84],"reinforced":[85],"framework":[86],"employs":[88],"novel":[90],"Think-with-Grounding":[91],"paradigm,":[92],"enabling":[93],"LLMs":[95],"actively":[97],"decide":[98],"when":[99,114],"perform":[101],"on-demand":[102],"grounding":[103,159,197,253],"during":[104],"interleaved":[105],"text\u2013video":[106],"reasoning,":[107],"selectively":[108],"zooming":[109],"into":[110],"question-relevant":[111],"clips":[112],"only":[113],"necessary.":[115],"Video-TwG":[116,225],"can":[117],"be":[118],"trained":[119],"end-to-end":[120],"straightforward":[123],"manner,":[124],"without":[125,259],"relying":[126],"on":[127,152,218],"auxiliary":[129],"modules":[130],"or":[131],"heavily":[132],"annotated":[133],"traces.":[135],"In":[136],"detail,":[137],"design":[139],"Two-stage":[141,238],"Reinforced":[142,239],"Curriculum":[143,240],"Strategy,":[144],"where":[145],"model":[147],"first":[148],"learns":[149],"think-with-grounding":[150,181],"behavior":[151],"small":[154],"short-video":[155],"GQA":[156],"dataset":[157,213],"with":[158,169],"labels,":[160],"then":[162],"scales":[163],"diverse":[165,172,248],"general":[166],"QA":[167,261],"data":[168,250],"domains":[173],"encourage":[175],"generalization.":[176],"Further,":[177],"handle":[179],"for":[183],"various":[184],"kinds":[185],"data,":[187],"TwG-GRPO":[191,245],"algorithm,":[192],"which":[193],"features":[194],"fine-grained":[196],"reward,":[198,201],"self-confirmed":[199],"pseudo":[200],"accuracy-gated":[203],"mechanism.":[204],"Finally,":[205],"construct":[209],"new":[211],"TwG-51K":[212],"facilitates":[215],"training.":[216],"Experiments":[217],"Video-MME,":[219],"LongVideoBench,":[220],"MLVU":[222],"show":[223],"consistently":[226],"outperforms":[227],"strong":[228],"LVU":[229],"baselines.":[230],"Further":[231],"ablation":[232],"validates":[233],"necessity":[235],"our":[237,244],"Strategy":[241],"shows":[243],"better":[246],"leverages":[247],"unlabeled":[249],"quality":[254],"reduce":[256],"redundant":[257],"groundings":[258],"sacrificing":[260],"performance.":[262],"https://github.com/hlchen23/Video-TwG":[263]},"counts_by_year":[],"updated_date":"2026-07-17T05:52:16.776730","created_date":"2026-07-16T00:00:00"}
