{"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/m-var-decoupled-scale-wise-autoregressive","title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","arxiv_id":"2411.10433","date":"2024-11-15","proceeding":null,"authors":["Sucheng Ren","Yaodong Yu","Nataniel Ruiz","Feng Wang","Alan Yuille","Cihang Xie"],"abstract":"There exists recent work in computer vision, named VAR, that proposes a new autoregressive paradigm for image generation. Diverging from the vanilla next-token prediction, VAR structurally reformulates the image generation into a coarse to fine next-scale prediction. In this paper, we show that this scale-wise autoregressive framework can be effectively decoupled into \\textit{intra-scale modeling}, which captures local spatial dependencies within each scale, and \\textit{inter-scale modeling}, which models cross-scale relationships progressively from coarse-to-fine scales. This decoupling structure allows to rebuild VAR in a more computationally efficient manner. Specifically, for intra-scale modeling -- crucial for generating high-fidelity images -- we retain the original bidirectional self-attention design to ensure comprehensive modeling; for inter-scale modeling, which semantically connects different scales but is computationally intensive, we apply linear-complexity mechanisms like Mamba to substantially reduce computational overhead. We term this new framework M-VAR. Extensive experiments demonstrate that our method outperforms existing models in both image quality and generation speed. For example, our 1.5B model, with fewer parameters and faster inference speed, outperforms the largest VAR-d30-2B. Moreover, our largest model M-VAR-d32 impressively registers 1.78 FID on ImageNet 256$\\times$256 and outperforms the prior-art autoregressive models LlamaGen/VAR by 0.4/0.19 and popular diffusion models LDM/DiT by 1.82/0.49, respectively. Code is avaiable at \\url{https://github.com/OliverRensu/MVAR}.","url_abs":"https://arxiv.org/abs/2411.10433v1","url_pdf":"https://arxiv.org/pdf/2411.10433v1.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":"m-var-decoupled-scale-wise-autoregressive","repo_url":"https://github.com/oliverrensu/mvar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"mamba","task_name":"Mamba"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"mamba","method_name":"Mamba"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.10433","atlas_url":"https://app.syntology.ai/?focus=2411.10433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10433"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oliverrensu/mvar","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran":2,"unverified":8},"by_repo_kind":{"official":{"samples":13,"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":13,"samples":[{"code_sha256_prefix":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/basic_vae.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"971ae8d2d8313e30","entry":"drop_path","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"971ae8d2d8313e30"}},{"code_sha256_prefix":"e543491ea064c733","entry":"gumbel_softmax_with_rng","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e543491ea064c733"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/basic_vae.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"80371584448f2f6e","entry":"sample_with_top_k_top_p_","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/helpers.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/helpers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80371584448f2f6e"}},{"code_sha256_prefix":"e847ee15f089dee6","entry":"allgather","repo":"oliverrensu/mvar","repo_kind":"official","path":"dist.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e847ee15f089dee6"}},{"code_sha256_prefix":"ff4c548fd07140d0","entry":"allreduce","repo":"oliverrensu/mvar","repo_kind":"official","path":"dist.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ff4c548fd07140d0"}},{"code_sha256_prefix":"8ff7703f731423de","entry":"build_dataset","repo":"oliverrensu/mvar","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/utils/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ff7703f731423de"}},{"code_sha256_prefix":"793c7e2489dd8dfc","entry":"make_attn","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/basic_vae.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/basic_vae.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"793c7e2489dd8dfc"}},{"code_sha256_prefix":"826ea3fc406a6a09","entry":"new_group","repo":"oliverrensu/mvar","repo_kind":"official","path":"dist.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/dist.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"826ea3fc406a6a09"}},{"code_sha256_prefix":"eabecb1bb23906fe","entry":"normalize_01_into_pm1","repo":"oliverrensu/mvar","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/utils/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eabecb1bb23906fe"}},{"code_sha256_prefix":"b1714d4e3b7ac3b9","entry":"pil_loader","repo":"oliverrensu/mvar","repo_kind":"official","path":"utils/data.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/utils/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b1714d4e3b7ac3b9"}},{"code_sha256_prefix":"f85408c04c9c626f","entry":"slow_attn","repo":"oliverrensu/mvar","repo_kind":"official","path":"models/basic_mvar.py","file_url":"https://github.com/oliverrensu/mvar/blob/HEAD/models/basic_mvar.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f85408c04c9c626f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}