{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/show-o2-improved-native-unified-multimodal","title":"Show-o2: Improved Native Unified Multimodal Models","arxiv_id":"2506.15564","date":"2025-06-18","proceeding":null,"authors":["Jinheng Xie","Zhenheng Yang","Mike Zheng Shou"],"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.","url_abs":"https://arxiv.org/abs/2506.15564v2","url_pdf":"https://arxiv.org/pdf/2506.15564v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"show-o2-improved-native-unified-multimodal","repo_url":"https://github.com/showlab/show-o","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.15564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15564"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/showlab/Show-o","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/showlab/show-o","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":6},"by_repo_kind":{"official":{"samples":11,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bac65c3dafaec040","entry":"apply_rotary_pos_emb","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/modules.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bac65c3dafaec040"}},{"code_sha256_prefix":"a8366f238618edad","entry":"get_constant_schedule","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/lr_schedulers.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/lr_schedulers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a8366f238618edad"}},{"code_sha256_prefix":"11f07821d1b2286b","entry":"get_constant_schedule_with_warmup","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/lr_schedulers.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/lr_schedulers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"11f07821d1b2286b"}},{"code_sha256_prefix":"1975e0c51e6f5753","entry":"get_linear_schedule_with_warmup","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/lr_schedulers.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/lr_schedulers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1975e0c51e6f5753"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/modules.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"3e268fcaaf4273fe","entry":"get_parameter_device","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/modeling_utils.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e268fcaaf4273fe"}},{"code_sha256_prefix":"33338f20f5619c59","entry":"get_parameter_dtype","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/modeling_utils.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33338f20f5619c59"}},{"code_sha256_prefix":"0a0354ad9a87e572","entry":"modulate","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/modules.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0a0354ad9a87e572"}},{"code_sha256_prefix":"10bfa31825ad417d","entry":"next_token_prediction","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/misc.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/misc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"10bfa31825ad417d"}},{"code_sha256_prefix":"ef3ce1218285e733","entry":"prepare_gen_input","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/misc.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/misc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ef3ce1218285e733"}},{"code_sha256_prefix":"6a27f4593c6fdc92","entry":"velocity_prediction","repo":"showlab/Show-o","repo_kind":"official","path":"show-o2/models/misc.py","file_url":"https://github.com/showlab/Show-o/blob/HEAD/show-o2/models/misc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6a27f4593c6fdc92"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}