{"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/a-phase-transition-in-diffusion-models","title":"A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data","arxiv_id":"2402.16991","date":"2024-02-26","proceeding":null,"authors":["Antonio Sclocchi","Alessandro Favero","Matthieu Wyart"],"abstract":"Understanding the structure of real data is paramount in advancing modern deep-learning methodologies. Natural data such as images are believed to be composed of features organized in a hierarchical and combinatorial manner, which neural networks capture during learning. Recent advancements show that diffusion models can generate high-quality images, hinting at their ability to capture this underlying compositional structure. We study this phenomenon in a hierarchical generative model of data. We find that the backward diffusion process acting after a time $t$ is governed by a phase transition at some threshold time, where the probability of reconstructing high-level features, like the class of an image, suddenly drops. Instead, the reconstruction of low-level features, such as specific details of an image, evolves smoothly across the whole diffusion process. This result implies that at times beyond the transition, the class has changed, but the generated sample may still be composed of low-level elements of the initial image. We validate these theoretical insights through numerical experiments on class-unconditional ImageNet diffusion models. Our analysis characterizes the relationship between time and scale in diffusion models and puts forward generative models as powerful tools to model combinatorial data properties.","url_abs":"https://arxiv.org/abs/2402.16991v3","url_pdf":"https://arxiv.org/pdf/2402.16991v3.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":"a-phase-transition-in-diffusion-models","repo_url":"https://github.com/pcsl-epfl/forward-backward-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.16991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16991"}},"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/pcsl-epfl/forward-backward-diffusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_honours":3,"ran":4,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":22,"ran":13,"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":"8ab9a97df8161f31","entry":"center_crop_arr","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/image_datasets.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/image_datasets.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ab9a97df8161f31"}},{"code_sha256_prefix":"cfd76fd0d89574a4","entry":"approx_standard_normal_cdf","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/losses.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/losses.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":"cfd76fd0d89574a4"}},{"code_sha256_prefix":"2ab2316ac6fdd869","entry":"betas_for_alpha_bar","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/gaussian_diffusion.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_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":"2ab2316ac6fdd869"}},{"code_sha256_prefix":"35572566acf61c78","entry":"create_named_schedule_sampler","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/resample.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/resample.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35572566acf61c78"}},{"code_sha256_prefix":"cd33283d615fb3d7","entry":"discretized_gaussian_log_likelihood","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/losses.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/losses.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":"cd33283d615fb3d7"}},{"code_sha256_prefix":"a086d6286a40b889","entry":"get_named_beta_schedule","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/gaussian_diffusion.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_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":"a086d6286a40b889"}},{"code_sha256_prefix":"e41367ad14ff58fd","entry":"get_param_groups_and_shapes","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/fp16_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/fp16_util.py","link_basis":"harvester_set","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":"e41367ad14ff58fd"}},{"code_sha256_prefix":"e20dd5102da3b050","entry":"make_master_params","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/fp16_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/fp16_util.py","link_basis":"harvester_set","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":"e20dd5102da3b050"}},{"code_sha256_prefix":"bcd8b4acab199405","entry":"make_output_format","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/logger.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/logger.py","link_basis":"harvester_set","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":"bcd8b4acab199405"}},{"code_sha256_prefix":"cf2798b666b231ca","entry":"normal_kl","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/losses.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/losses.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":"cf2798b666b231ca"}},{"code_sha256_prefix":"9b6e4e070473e76f","entry":"space_timesteps","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/respace.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/respace.py","link_basis":"harvester_set","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":"9b6e4e070473e76f"}},{"code_sha256_prefix":"64fff1e30802b815","entry":"unflatten_master_params","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/fp16_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/fp16_util.py","link_basis":"harvester_set","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":"64fff1e30802b815"}},{"code_sha256_prefix":"129b804760b3115f","entry":"zero_module","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/nn.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/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":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/nn.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/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":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/nn.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/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"}},{"code_sha256_prefix":"5e5d99a81705a07f","entry":"create_classifier_and_diffusion","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/script_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/script_util.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":"5e5d99a81705a07f"}},{"code_sha256_prefix":"35ea054532112e53","entry":"create_model","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/script_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/script_util.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":"35ea054532112e53"}},{"code_sha256_prefix":"6a3cfc58dafbe392","entry":"create_model_and_diffusion","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/script_util.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/script_util.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":"6a3cfc58dafbe392"}},{"code_sha256_prefix":"2f10546095747e84","entry":"load_classifier","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/torch_classifiers.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/torch_classifiers.py","link_basis":"first_harvest_node","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":"2f10546095747e84"}},{"code_sha256_prefix":"e515a67f7f32e76d","entry":"mpi_weighted_mean","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/logger.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/logger.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":"e515a67f7f32e76d"}},{"code_sha256_prefix":"0c6607473a4c4c55","entry":"profile","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/logger.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/logger.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":"0c6607473a4c4c55"}},{"code_sha256_prefix":"53d5be4fdbcfac23","entry":"random_crop_arr","repo":"pcsl-epfl/forward-backward-diffusion","repo_kind":"official","path":"guided_diffusion/image_datasets.py","file_url":"https://github.com/pcsl-epfl/forward-backward-diffusion/blob/HEAD/guided_diffusion/image_datasets.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":"53d5be4fdbcfac23"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}