{"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/understanding-is-compression","title":"Lossless data compression by large models","arxiv_id":"2407.07723","date":"2024-06-24","proceeding":null,"authors":["Ziguang Li","Chao Huang","Xuliang Wang","Haibo Hu","Cole Wyeth","Dongbo Bu","Quan Yu","Wen Gao","Xingwu Liu","Ming Li"],"abstract":"Modern data compression methods are slowly reaching their limits after 80 years of research, millions of papers, and wide range of applications. Yet, the extravagant 6G communication speed requirement raises a major open question for revolutionary new ideas of data compression. We have previously shown all understanding or learning are compression, under reasonable assumptions. Large language models (LLMs) understand data better than ever before. Can they help us to compress data? The LLMs may be seen to approximate the uncomputable Solomonoff induction. Therefore, under this new uncomputable paradigm, we present LMCompress. LMCompress shatters all previous lossless compression algorithms, doubling the lossless compression ratios of JPEG-XL for images, FLAC for audios, and H.264 for videos, and quadrupling the compression ratio of bz2 for texts. The better a large model understands the data, the better LMCompress compresses.","url_abs":"https://arxiv.org/abs/2407.07723v3","url_pdf":"https://arxiv.org/pdf/2407.07723v3.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":"understanding-is-compression","repo_url":"https://github.com/mcGill-NLP/medal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"data-compression","task_name":"Data Compression"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.07723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07723"}},"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/mcGill-NLP/medal","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":3},"by_repo_kind":{"official":{"samples":9,"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":9,"samples":[{"code_sha256_prefix":"cba10c551fb3c323","entry":"load_dataframes","repo":"mcGill-NLP/medal","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cba10c551fb3c323"}},{"code_sha256_prefix":"8155689bc5957966","entry":"load_mimic_mortality","repo":"mcGill-NLP/medal","repo_kind":"official","path":"downstream/utils.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/downstream/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8155689bc5957966"}},{"code_sha256_prefix":"0c2a1f556b1e44d6","entry":"load_model","repo":"mcGill-NLP/medal","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c2a1f556b1e44d6"}},{"code_sha256_prefix":"ef7adb5972287dde","entry":"lstm","repo":"mcGill-NLP/medal","repo_kind":"official","path":"hubconf.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/hubconf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ef7adb5972287dde"}},{"code_sha256_prefix":"22270589c7ec7481","entry":"lstm_sa","repo":"mcGill-NLP/medal","repo_kind":"official","path":"hubconf.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/hubconf.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"22270589c7ec7481"}},{"code_sha256_prefix":"eb090d26e716d944","entry":"prepare_label","repo":"mcGill-NLP/medal","repo_kind":"official","path":"downstream/tokenizer_and_dataset.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/downstream/tokenizer_and_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb090d26e716d944"}},{"code_sha256_prefix":"71a9ba6b952ddf00","entry":"electra","repo":"mcGill-NLP/medal","repo_kind":"official","path":"hubconf.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/hubconf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71a9ba6b952ddf00"}},{"code_sha256_prefix":"ba02ce5ab3059cd9","entry":"evaluate","repo":"mcGill-NLP/medal","repo_kind":"official","path":"utils.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ba02ce5ab3059cd9"}},{"code_sha256_prefix":"9de277840306a450","entry":"load_mimic_diagnosis","repo":"mcGill-NLP/medal","repo_kind":"official","path":"downstream/utils.py","file_url":"https://github.com/mcGill-NLP/medal/blob/HEAD/downstream/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9de277840306a450"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}