{"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/mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","arxiv_id":"2505.15809","date":"2025-05-21","proceeding":null,"authors":["Ling Yang","Ye Tian","Bowen Li","Xinchen Zhang","Ke Shen","Yunhai Tong","Mengdi Wang"],"abstract":"We introduce MMaDA, a novel class of multimodal diffusion foundation models designed to achieve superior performance across diverse domains such as textual reasoning, multimodal understanding, and text-to-image generation. The approach is distinguished by three key innovations: (i) MMaDA adopts a unified diffusion architecture with a shared probabilistic formulation and a modality-agnostic design, eliminating the need for modality-specific components. This architecture ensures seamless integration and processing across different data types. (ii) We implement a mixed long chain-of-thought (CoT) fine-tuning strategy that curates a unified CoT format across modalities. By aligning reasoning processes between textual and visual domains, this strategy facilitates cold-start training for the final reinforcement learning (RL) stage, thereby enhancing the model's ability to handle complex tasks from the outset. (iii) We propose UniGRPO, a unified policy-gradient-based RL algorithm specifically tailored for diffusion foundation models. Utilizing diversified reward modeling, UniGRPO unifies post-training across both reasoning and generation tasks, ensuring consistent performance improvements. Experimental results demonstrate that MMaDA-8B exhibits strong generalization capabilities as a unified multimodal foundation model. It surpasses powerful models like LLaMA-3-7B and Qwen2-7B in textual reasoning, outperforms Show-o and SEED-X in multimodal understanding, and excels over SDXL and Janus in text-to-image generation. These achievements highlight MMaDA's effectiveness in bridging the gap between pretraining and post-training within unified diffusion architectures, providing a comprehensive framework for future research and development. We open-source our code and trained models at: https://github.com/Gen-Verse/MMaDA","url_abs":"https://arxiv.org/abs/2505.15809v1","url_pdf":"https://arxiv.org/pdf/2505.15809v1.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":"mmada-multimodal-large-diffusion-language","repo_url":"https://github.com/gen-verse/mmada","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.15809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15809"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gen-verse/mmada","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Gen-Verse/MMaDA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_fixture":1,"ran":1,"unverified":4},"by_repo_kind":{"official":{"samples":9,"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":"c3a6b977022957cb","entry":"Normalize","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/common_modules.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/common_modules.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3a6b977022957cb"}},{"code_sha256_prefix":"a5334721ab55f48f","entry":"add_gumbel_noise","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"generate.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/generate.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5334721ab55f48f"}},{"code_sha256_prefix":"6f22da9cc766ffbe","entry":"get_num_transfer_tokens","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"generate.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/generate.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6f22da9cc766ffbe"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/common_modules.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/common_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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"2d82abbef2c4addb","entry":"unpack_time","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/common_modules.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/common_modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d82abbef2c4addb"}},{"code_sha256_prefix":"615ec9b280bef7c6","entry":"add_gumbel_noise","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/modeling_mmada.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/modeling_mmada.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"615ec9b280bef7c6"}},{"code_sha256_prefix":"bdb7c183d8696b6b","entry":"generate","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"generate.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/generate.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bdb7c183d8696b6b"}},{"code_sha256_prefix":"376bf22d5737fc2a","entry":"get_logger","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/logging.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/logging.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"376bf22d5737fc2a"}},{"code_sha256_prefix":"65934529afeabeff","entry":"get_num_transfer_tokens","repo":"Gen-Verse/MMaDA","repo_kind":"official","path":"models/modeling_mmada.py","file_url":"https://github.com/Gen-Verse/MMaDA/blob/HEAD/models/modeling_mmada.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65934529afeabeff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}