{"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/latent-diffusion-for-language-generation-1","title":"Latent Diffusion for Language Generation","arxiv_id":"2212.09462","date":"2022-12-19","proceeding":"NeurIPS 2023 11","authors":["Justin Lovelace","Varsha Kishore","Chao Wan","Eliot Shekhtman","Kilian Q. Weinberger"],"abstract":"Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have presented diffusion as an alternative to existing pretrained language models. We view diffusion and existing language models as complementary. We demonstrate that encoder-decoder language models can be utilized to efficiently learn high-quality language autoencoders. We then demonstrate that continuous diffusion models can be learned in the latent space of the language autoencoder, enabling us to sample continuous latent representations that can be decoded into natural language with the pretrained decoder. We validate the effectiveness of our approach for unconditional, class-conditional, and sequence-to-sequence language generation. We demonstrate across multiple diverse data sets that our latent language diffusion models are significantly more effective than previous diffusion language models.","url_abs":"https://arxiv.org/abs/2212.09462v2","url_pdf":"https://arxiv.org/pdf/2212.09462v2.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":"latent-diffusion-for-language-generation-1","repo_url":"https://github.com/justinlovelace/latent-diffusion-for-language","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.09462","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09462"}},"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/justinlovelace/latent-diffusion-for-language","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_honours":3,"ran_draft_wrong":4,"ran_violates":1},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":"e7b1995f962c95ba","entry":"GaussianDiffusion","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7b1995f962c95ba"}},{"code_sha256_prefix":"d5b5906bd8d6f099","entry":"alpha_to_shifted_log_snr","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","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":"d5b5906bd8d6f099"}},{"code_sha256_prefix":"e619cd65a90a008c","entry":"beta_linear_schedule","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","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":"e619cd65a90a008c"}},{"code_sha256_prefix":"59dbcc3beaee75d7","entry":"cosine_schedule","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.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":"59dbcc3beaee75d7"}},{"code_sha256_prefix":"d93be7ef30d67f1e","entry":"log","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.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":"d93be7ef30d67f1e"}},{"code_sha256_prefix":"8697654fdac09b54","entry":"log_snr_to_alpha","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","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":"8697654fdac09b54"}},{"code_sha256_prefix":"8cd8e6547ade35f4","entry":"right_pad_dims_to","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8cd8e6547ade35f4"}},{"code_sha256_prefix":"cf03aea4a2411cc6","entry":"sigmoid_schedule","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.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":"cf03aea4a2411cc6"}},{"code_sha256_prefix":"adb4575b401b32ab","entry":"simple_linear_schedule","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","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":"adb4575b401b32ab"}},{"code_sha256_prefix":"13dc3dd849ea08a9","entry":"time_to_alpha","repo":"justinlovelace/latent-diffusion-for-language","repo_kind":"official","path":"diffusion/text_denoising_diffusion.py","file_url":"https://github.com/justinlovelace/latent-diffusion-for-language/blob/HEAD/diffusion/text_denoising_diffusion.py","link_basis":"first_harvest_node","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":"13dc3dd849ea08a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}