{"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/switch-diffusion-transformer-synergizing","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","arxiv_id":"2403.09176","date":"2024-03-14","proceeding":null,"authors":["Byeongjun Park","Hyojun Go","Jin-Young Kim","Sangmin Woo","Seokil Ham","Changick Kim"],"abstract":"Diffusion models have achieved remarkable success across a range of generative tasks. Recent efforts to enhance diffusion model architectures have reimagined them as a form of multi-task learning, where each task corresponds to a denoising task at a specific noise level. While these efforts have focused on parameter isolation and task routing, they fall short of capturing detailed inter-task relationships and risk losing semantic information, respectively. In response, we introduce Switch Diffusion Transformer (Switch-DiT), which establishes inter-task relationships between conflicting tasks without compromising semantic information. To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation. Additionally, we propose a diffusion prior loss, encouraging similar tasks to share their denoising paths while isolating conflicting ones. Through these, each transformer block contains a shared expert across all tasks, where the common and task-specific denoising paths enable the diffusion model to construct its beneficial way of synergizing denoising tasks. Extensive experiments validate the effectiveness of our approach in improving both image quality and convergence rate, and further analysis demonstrates that Switch-DiT constructs tailored denoising paths across various generation scenarios.","url_abs":"https://arxiv.org/abs/2403.09176v2","url_pdf":"https://arxiv.org/pdf/2403.09176v2.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":"switch-diffusion-transformer-synergizing","repo_url":"https://github.com/byeongjun-park/Switch-DiT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"switch-diffusion-transformer-synergizing","repo_url":"https://github.com/byeongjun-park/SteerX","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.09176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09176"}},"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/byeongjun-park/Switch-DiT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/byeongjun-park/SteerX","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":5,"ran":5,"ran_honours":3,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":18,"ran":14,"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":"d6a68e210556f857","entry":"approx_standard_normal_cdf","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/diffusion_utils.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":"d6a68e210556f857"}},{"code_sha256_prefix":"7025a15a914aa29c","entry":"bipartite_matching","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"util/model_util.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/util/model_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7025a15a914aa29c"}},{"code_sha256_prefix":"cab0618c0a02c1dd","entry":"compute_gating","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"util/model_util.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/util/model_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cab0618c0a02c1dd"}},{"code_sha256_prefix":"ab1c9568b4e13899","entry":"continuous_gaussian_log_likelihood","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/diffusion_utils.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":"ab1c9568b4e13899"}},{"code_sha256_prefix":"65dba4593dc4b27d","entry":"create_mask_tasks","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"models/DiT/models.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/models/DiT/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65dba4593dc4b27d"}},{"code_sha256_prefix":"0562beb66a52dbef","entry":"create_mask_tasks","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"models/taskrouting.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/models/taskrouting.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0562beb66a52dbef"}},{"code_sha256_prefix":"7b21a01ae77703a3","entry":"create_npz_from_sample_folder","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"sample_ddp.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/sample_ddp.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b21a01ae77703a3"}},{"code_sha256_prefix":"c92c27c924b517e8","entry":"get_2d_sincos_pos_embed","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"models/DiT/models.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/models/DiT/models.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c92c27c924b517e8"}},{"code_sha256_prefix":"3e0fa4efc22272d4","entry":"get_beta_schedule","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/gaussian_diffusion.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e0fa4efc22272d4"}},{"code_sha256_prefix":"f6d7c009a8efb8b7","entry":"mean_flat","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/gaussian_diffusion.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":"f6d7c009a8efb8b7"}},{"code_sha256_prefix":"03310bba324ae4fb","entry":"modulate","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"util/model_util.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/util/model_util.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":"03310bba324ae4fb"}},{"code_sha256_prefix":"8afbfc42c6ea0448","entry":"normal_kl","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/diffusion_utils.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/diffusion_utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8afbfc42c6ea0448"}},{"code_sha256_prefix":"567312c76772b0dd","entry":"sample_t_batch","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"models/UW.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/models/UW.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"567312c76772b0dd"}},{"code_sha256_prefix":"ea9dbc131adf582e","entry":"space_timesteps","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/respace.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/respace.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea9dbc131adf582e"}},{"code_sha256_prefix":"6a0d5ecd441905cc","entry":"download_model","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"download.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/download.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":"6a0d5ecd441905cc"}},{"code_sha256_prefix":"29947a0a94157558","entry":"find_model","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"download.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/download.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":"29947a0a94157558"}},{"code_sha256_prefix":"665d8a4e8f673a4c","entry":"get_2d_sincos_pos_embed_from_grid","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"models/DiT/models.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/models/DiT/models.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":"665d8a4e8f673a4c"}},{"code_sha256_prefix":"4f55c34a92359642","entry":"get_named_beta_schedule","repo":"byeongjun-park/Switch-DiT","repo_kind":"official","path":"diffusion/gaussian_diffusion.py","file_url":"https://github.com/byeongjun-park/Switch-DiT/blob/HEAD/diffusion/gaussian_diffusion.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":"4f55c34a92359642"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}