{"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/discriminator-guided-cooperative-diffusion","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","arxiv_id":"2405.17842","date":"2024-05-28","proceeding":null,"authors":["Akio Hayakawa","Masato Ishii","Takashi Shibuya","Yuki Mitsufuji"],"abstract":"This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal models to cooperatively generate well-aligned samples across modalities. Specifically, given two pre-trained base diffusion models, we train a lightweight joint guidance module to adjust scores separately estimated by the base models to match the score of joint distribution over audio and video. We show that this guidance can be computed using the gradient of the optimal discriminator, which distinguishes real audio-video pairs from fake ones independently generated by the base models. Based on this analysis, we construct a joint guidance module by training this discriminator. Additionally, we adopt a loss function to stabilize the discriminator's gradient and make it work as a noise estimator, as in standard diffusion models. Empirical evaluations on several benchmark datasets demonstrate that our method improves both single-modal fidelity and multimodal alignment with relatively few parameters. The code is available at: https://github.com/SonyResearch/MMDisCo.","url_abs":"https://arxiv.org/abs/2405.17842v2","url_pdf":"https://arxiv.org/pdf/2405.17842v2.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":"discriminator-guided-cooperative-diffusion","repo_url":"https://github.com/sonyresearch/mmdisco","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"video-generation","task_name":"Video Generation"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.17842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17842"}},"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/SonyResearch/MMDisCo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sonyresearch/mmdisco","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran_fixture":1,"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"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":"deda81553b270226","entry":"expand_dims","repo":"sonyresearch/mmdisco","repo_kind":"official","path":"mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.py","file_url":"https://github.com/sonyresearch/mmdisco/blob/HEAD/mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deda81553b270226"}},{"code_sha256_prefix":"0f0757aa08450a2c","entry":"interpolate_fn","repo":"sonyresearch/mmdisco","repo_kind":"official","path":"mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.py","file_url":"https://github.com/sonyresearch/mmdisco/blob/HEAD/mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f0757aa08450a2c"}},{"code_sha256_prefix":"dc75210a9821cfbc","entry":"model_wrapper","repo":"sonyresearch/mmdisco","repo_kind":"official","path":"mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.py","file_url":"https://github.com/sonyresearch/mmdisco/blob/HEAD/mmdisco/models/diffusion/mmdiffusion/multimodal_dpm_solver_plus.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc75210a9821cfbc"}},{"code_sha256_prefix":"a6fda49da39336fb","entry":"spectral_normalize","repo":"SonyResearch/MMDisCo","repo_kind":"official","path":"mmdisco/models/diffusion/mel_extractor.py","file_url":"https://github.com/SonyResearch/MMDisCo/blob/HEAD/mmdisco/models/diffusion/mel_extractor.py","link_basis":"first_harvest_node","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":"a6fda49da39336fb"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"SonyResearch/MMDisCo","repo_kind":"official","path":"mmdisco/models/residual_predictor/nn.py","file_url":"https://github.com/SonyResearch/MMDisCo/blob/HEAD/mmdisco/models/residual_predictor/nn.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":"129b804760b3115f"}},{"code_sha256_prefix":"ecd0fc28815b65ae","entry":"avg_pool_nd","repo":"SonyResearch/MMDisCo","repo_kind":"official","path":"mmdisco/models/residual_predictor/nn.py","file_url":"https://github.com/SonyResearch/MMDisCo/blob/HEAD/mmdisco/models/residual_predictor/nn.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":"ecd0fc28815b65ae"}},{"code_sha256_prefix":"fe4eb545bbb728e0","entry":"conv_nd","repo":"SonyResearch/MMDisCo","repo_kind":"official","path":"mmdisco/models/residual_predictor/nn.py","file_url":"https://github.com/SonyResearch/MMDisCo/blob/HEAD/mmdisco/models/residual_predictor/nn.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":"fe4eb545bbb728e0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}