{"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/disco-diff-enhancing-continuous-diffusion","title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","arxiv_id":"2407.03300","date":"2024-07-03","proceeding":null,"authors":["Yilun Xu","Gabriele Corso","Tommi Jaakkola","Arash Vahdat","Karsten Kreis"],"abstract":"Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, potentially multimodal data distribution into a single continuous Gaussian distribution arguably represents an unnecessarily challenging learning problem. We propose Discrete-Continuous Latent Variable Diffusion Models (DisCo-Diff) to simplify this task by introducing complementary discrete latent variables. We augment DMs with learnable discrete latents, inferred with an encoder, and train DM and encoder end-to-end. DisCo-Diff does not rely on pre-trained networks, making the framework universally applicable. The discrete latents significantly simplify learning the DM's complex noise-to-data mapping by reducing the curvature of the DM's generative ODE. An additional autoregressive transformer models the distribution of the discrete latents, a simple step because DisCo-Diff requires only few discrete variables with small codebooks. We validate DisCo-Diff on toy data, several image synthesis tasks as well as molecular docking, and find that introducing discrete latents consistently improves model performance. For example, DisCo-Diff achieves state-of-the-art FID scores on class-conditioned ImageNet-64/128 datasets with ODE sampler.","url_abs":"https://arxiv.org/abs/2407.03300v1","url_pdf":"https://arxiv.org/pdf/2407.03300v1.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":"disco-diff-enhancing-continuous-diffusion","repo_url":"https://github.com/gcorso/disco-diffdock","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"molecular-docking","task_name":"Molecular Docking"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-128x128","task":"Image Generation","dataset":"ImageNet 128x128","model":"DisCo-Diff","rank_in_archive_order":3,"of":23,"metrics":{"FID":"1.73"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-64x64","task":"Image Generation","dataset":"ImageNet 64x64","model":"DisCo-Diff","rank_in_archive_order":7,"of":65,"metrics":{"FID":"1.22"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.03300","atlas_url":"https://app.syntology.ai/?focus=2407.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03300"}},"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/gcorso/disco-diffdock","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_violates":2},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":"1c0b14628ac6030e","entry":"FCBlock","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/models/layers.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":"1c0b14628ac6030e"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/models/layers.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"models/layers.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/models/layers.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"ec9850ba4d4020d9","entry":"get_irrep_seq","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"models/tensor_layers.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/models/tensor_layers.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":"ec9850ba4d4020d9"}},{"code_sha256_prefix":"fb560460839637bc","entry":"irrep_to_size","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"models/tensor_layers.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/models/tensor_layers.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":"fb560460839637bc"}},{"code_sha256_prefix":"84fa10d86ca431c9","entry":"remove_data_parallel","repo":"gcorso/disco-diffdock","repo_kind":"official","path":"utils/model_utils.py","file_url":"https://github.com/gcorso/disco-diffdock/blob/HEAD/utils/model_utils.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":"84fa10d86ca431c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}