{"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/parallel-and-flexible-sampling-from","title":"Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics","arxiv_id":"2105.08164","date":"2021-05-17","proceeding":null,"authors":["Vivek Jayaram","John Thickstun"],"abstract":"This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propose a sampling procedure that initializes a sequence with white noise and follows a Markov chain defined by Langevin dynamics on the global log-likelihood of the sequence. This approach parallelizes the sampling process and generalizes to conditional sampling. Using an autoregressive model as a Bayesian prior, we can steer the output of a generative model using a conditional likelihood or constraints. We apply these techniques to autoregressive models in the visual and audio domains, with competitive results for audio source separation, super-resolution, and inpainting.","url_abs":"https://arxiv.org/abs/2105.08164v2","url_pdf":"https://arxiv.org/pdf/2105.08164v2.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":"parallel-and-flexible-sampling-from","repo_url":"https://github.com/vivjay30/pnf-sampling","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"audio-source-separation","task_name":"Audio Source Separation"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.08164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.08164"}},"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/vivjay30/pnf-sampling","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"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":"1b589fa04d754fdf","entry":"cyclic_cosine_annealing","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/lrschedule.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/lrschedule.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":"1b589fa04d754fdf"}},{"code_sha256_prefix":"e1dfe71f884480d1","entry":"get_paths_by_glob","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/preprocess_normalize.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/preprocess_normalize.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":"e1dfe71f884480d1"}},{"code_sha256_prefix":"4b1bfc1d38d07b48","entry":"low_cut_filter","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/audio.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/audio.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":"4b1bfc1d38d07b48"}},{"code_sha256_prefix":"3f5fdf4636f5ba45","entry":"noam_learning_rate_decay","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/lrschedule.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/lrschedule.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":"3f5fdf4636f5ba45"}},{"code_sha256_prefix":"c4027950e9b2bfa5","entry":"read_wav_or_raw","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/mksubset.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/mksubset.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":"c4027950e9b2bfa5"}},{"code_sha256_prefix":"0403b56a2eeb1c81","entry":"si_sdr","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/eval_data_loader.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/eval_data_loader.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":"0403b56a2eeb1c81"}},{"code_sha256_prefix":"2091f12427c3b654","entry":"snr","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/evaluate.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/evaluate.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":"2091f12427c3b654"}},{"code_sha256_prefix":"a8c3b8fb903acda7","entry":"step_learning_rate_decay","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/lrschedule.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/lrschedule.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":"a8c3b8fb903acda7"}},{"code_sha256_prefix":"b71103ee25d18914","entry":"to_int16","repo":"vivjay30/pnf-sampling","repo_kind":"official","path":"pnf-wavenet/evaluate.py","file_url":"https://github.com/vivjay30/pnf-sampling/blob/HEAD/pnf-wavenet/evaluate.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":"b71103ee25d18914"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}