{"work":{"id":"221fe55b-b4fc-4277-b4ad-6fcf8adb777a","openalex_id":null,"doi":null,"arxiv_id":"2506.00123","raw_key":null,"title":"Visual embodied brain: Let multimodal large language models see, think, and control in spaces.arXiv preprint arXiv:2506.00123, 2025","authors":null,"authors_text":"Gen Luo, Ganlin Yang, Ziyang Gong, Guanzhou Chen, Haonan Duan, Erfei Cui, Ronglei Tong, Zhi Hou, Tianyi Zhang, Zhe Chen, Shenglong Ye, Lewei Lu, Jingbo Wang, Wenhai Wang, Jifeng Dai, Yu Qiao, Rongrong Ji, and Xizhou Zhu","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2506.00123","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-03T15:28:34.757769+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T05:56:00.248556+00:00","updated_at":"2026-07-03T15:28:34.757769+00:00","title_quality_ok":true,"display_title":"Visual embodied brain: Let multimodal large language models see, think, and control in spaces","render_title":"Visual embodied brain: Let multimodal large language models see, think, and control in spaces"},"hub":{"state":{"work_id":"221fe55b-b4fc-4277-b4ad-6fcf8adb777a","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":14,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2025-08-16T13:37:11+00:00","last_pith_cited_at":"2026-06-14T11:30:42+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":"2026-07-04T08:36:44.744921+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}