{"work":{"id":"14ae45e8-e465-4230-99bf-0a2a191dabfd","openalex_id":null,"doi":null,"arxiv_id":"2507.12440","raw_key":null,"title":"Egovla: Learning vision-language-action models from egocentric human videos.arXiv preprint arXiv:2507.12440, 2025","authors":null,"authors_text":"Ruihan Yang, Qinxi Yu, Yecheng Wu, Rui Yan, Borui Li, An-Chieh Cheng, Xueyan Zou, Yunhao Fang, Xuxin Cheng, Ri-Zhao Qiu, et al","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2507.12440","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-20T11:13:13.400232+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T11:45:21.755447+00:00","updated_at":"2026-05-20T11:13:13.400232+00:00","title_quality_ok":true,"display_title":"Egovla: Learning vision-language-action models from egocentric human videos","render_title":"Egovla: Learning vision-language-action models from egocentric human videos"},"hub":{"state":{"work_id":"14ae45e8-e465-4230-99bf-0a2a191dabfd","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2026-02-06T18:49:43+00:00","last_pith_cited_at":"2026-05-18T17:50:32+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-20T13:11:52.515085+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":11},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":12}],"runs":{},"summary":{},"graph":{},"authors":[]}}