{"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/unlocking-the-capabilities-of-masked","title":"Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance","arxiv_id":"2410.13136","date":"2024-10-17","proceeding":null,"authors":["Jiwan Hur","Dong-Jae Lee","Gyojin Han","Jaehyun Choi","Yunho Jeon","Junmo Kim"],"abstract":"Masked generative models (MGMs) have shown impressive generative ability while providing an order of magnitude efficient sampling steps compared to continuous diffusion models. However, MGMs still underperform in image synthesis compared to recent well-developed continuous diffusion models with similar size in terms of quality and diversity of generated samples. A key factor in the performance of continuous diffusion models stems from the guidance methods, which enhance the sample quality at the expense of diversity. In this paper, we extend these guidance methods to generalized guidance formulation for MGMs and propose a self-guidance sampling method, which leads to better generation quality. The proposed approach leverages an auxiliary task for semantic smoothing in vector-quantized token space, analogous to the Gaussian blur in continuous pixel space. Equipped with the parameter-efficient fine-tuning method and high-temperature sampling, MGMs with the proposed self-guidance achieve a superior quality-diversity trade-off, outperforming existing sampling methods in MGMs with more efficient training and sampling costs. Extensive experiments with the various sampling hyperparameters confirm the effectiveness of the proposed self-guidance.","url_abs":"https://arxiv.org/abs/2410.13136v1","url_pdf":"https://arxiv.org/pdf/2410.13136v1.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":"unlocking-the-capabilities-of-masked","repo_url":"https://github.com/jiwanhur/unlockmgm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.13136","atlas_url":"https://app.syntology.ai/?focus=2410.13136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13136"}},"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/jiwanhur/unlockmgm","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":6,"ran_fixture":2,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"repositories":1},"community":{"samples":4,"ran":4,"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":8,"samples":[{"code_sha256_prefix":"ef8d9a0b717d3cb0","entry":"flatten_omega_conf","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"training/train_maskgit_imagenet.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/training/train_maskgit_imagenet.py","link_basis":"plan_row","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":"ef8d9a0b717d3cb0"}},{"code_sha256_prefix":"b22b48bb429101bb","entry":"make_attention_mask","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b22b48bb429101bb"}},{"code_sha256_prefix":"e88526ab8fc3ebc4","entry":"make_attention_mask","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_transformer.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_transformer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e88526ab8fc3ebc4"}},{"code_sha256_prefix":"1a6c10e37cb97711","entry":"prob_mask_like","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a6c10e37cb97711"}},{"code_sha256_prefix":"162f6eae613812c6","entry":"prob_mask_like","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_transformer.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_transformer.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"162f6eae613812c6"}},{"code_sha256_prefix":"d8437c41cc2a860f","entry":"soft_target_cross_entropy","repo":"huggingface/open-muse","repo_kind":"community","path":"training/train_maskgit_imagenet.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/training/train_maskgit_imagenet.py","link_basis":"first_harvest_node","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":"d8437c41cc2a860f"}},{"code_sha256_prefix":"7daf2f4e6899de97","entry":"uniform","repo":"huggingface/open-muse","repo_kind":"community","path":"muse/modeling_transformer.py","file_url":"https://github.com/huggingface/open-muse/blob/HEAD/muse/modeling_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7daf2f4e6899de97"}},{"code_sha256_prefix":"66e51521e0875290","entry":"uniform","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_transformer.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_transformer.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"66e51521e0875290"}},{"code_sha256_prefix":"4c71b9128b894511","entry":"Normalize","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_movq.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_movq.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":"4c71b9128b894511"}},{"code_sha256_prefix":"bfdddec04a7257ca","entry":"get_parameter_device","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_utils.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_utils.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":"bfdddec04a7257ca"}},{"code_sha256_prefix":"4f52e71d06a15422","entry":"get_parameter_dtype","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_utils.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_utils.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":"4f52e71d06a15422"}},{"code_sha256_prefix":"934f2eb98d647821","entry":"load_state_dict","repo":"jiwanhur/unlockmgm","repo_kind":"official","path":"muse/modeling_utils.py","file_url":"https://github.com/jiwanhur/unlockmgm/blob/HEAD/muse/modeling_utils.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":"934f2eb98d647821"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}