{"work":{"id":"77f00563-1ce6-4fba-9d4e-c8ce83f716ac","openalex_id":null,"doi":null,"arxiv_id":"2506.15564","raw_key":null,"title":"Show-o2: Improved Native Unified Multimodal Models","authors":null,"authors_text":"Jinheng Xie, Zhenheng Yang, Mike Zheng Shou","year":2025,"venue":"cs.CV","abstract":"This paper presents improved native unified multimodal models, \\emph{i.e.,} Show-o2, that leverage autoregressive modeling and flow matching. Built upon a 3D causal variational autoencoder space, unified visual representations are constructed through a dual-path of spatial (-temporal) fusion, enabling scalability across image and video modalities while ensuring effective multimodal understanding and generation. Based on a language model, autoregressive modeling and flow matching are natively applied to the language head and flow head, respectively, to facilitate text token prediction and image/video generation. A two-stage training recipe is designed to effectively learn and scale to larger models. The resulting Show-o2 models demonstrate versatility in handling a wide range of multimodal understanding and generation tasks across diverse modalities, including text, images, and videos. Code and models are released at https://github.com/showlab/Show-o.","external_url":"https://arxiv.org/abs/2506.15564","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-21T14:50:14.696177+00:00","pith_arxiv_id":"2506.15564","created_at":"2026-05-09T23:24:42.980799+00:00","updated_at":"2026-05-21T14:50:14.696177+00:00","title_quality_ok":true,"display_title":"Show-o2: Improved Native Unified Multimodal Models","render_title":"Show-o2: Improved Native Unified Multimodal Models"},"hub":{"state":{"work_id":"77f00563-1ce6-4fba-9d4e-c8ce83f716ac","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":41,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-08-04T11:49:20+00:00","last_pith_cited_at":"2026-05-18T18:00:04+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":"2026-05-25T05:55:29.164107+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":12},{"context_role":"baseline","n":8},{"context_role":"method","n":2},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":12},{"context_polarity":"baseline","n":8},{"context_polarity":"use_method","n":2},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}