Language Modeling Is Compression Article Swipe
Grégoire Delétang
,
Anian Ruoss
,
Paul-Ambroise Duquenne
,
Elliot Catt
,
Tim Genewein
,
Christopher Mattern
,
Jordi Grau-Moya
,
Li Kevin Wenliang
,
Matthew Aitchison
,
Laurent Orseau
,
Marcus Hütter
,
Joel Veness
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.10668
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2309.10668
It has long been established that predictive models can be transformed into lossless compressors and vice versa. Incidentally, in recent years, the machine learning community has focused on training increasingly large and powerful self-supervised (language) models. Since these large language models exhibit impressive predictive capabilities, they are well-positioned to be strong compressors. In this work, we advocate for viewing the prediction problem through the lens of compression and evaluate the compression capabilities of large (foundation) models. We show that large language models are powerful general-purpose predictors and that the compression viewpoint provides novel insights into scaling laws, tokenization, and in-context learning. For example, Chinchilla 70B, while trained primarily on text, compresses ImageNet patches to 43.4% and LibriSpeech samples to 16.4% of their raw size, beating domain-specific compressors like PNG (58.5%) or FLAC (30.3%), respectively. Finally, we show that the prediction-compression equivalence allows us to use any compressor (like gzip) to build a conditional generative model.
Related Topics
Concepts
Lossless compression
Computer science
Lossy compression
Language model
Gas compressor
Compression (physics)
Context (archaeology)
Data compression
Artificial intelligence
Natural language processing
Machine learning
Speech recognition
Engineering
Mechanical engineering
Materials science
Composite material
Paleontology
Biology
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2309.10668
- https://arxiv.org/pdf/2309.10668
- OA Status
- green
- Cited By
- 26
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4386908184
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4386908184Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2309.10668Digital Object Identifier
- Title
-
Language Modeling Is CompressionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-09-19Full publication date if available
- Authors
-
Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hütter, Joel VenessList of authors in order
- Landing page
-
https://arxiv.org/abs/2309.10668Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2309.10668Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2309.10668Direct OA link when available
- Concepts
-
Lossless compression, Computer science, Lossy compression, Language model, Gas compressor, Compression (physics), Context (archaeology), Data compression, Artificial intelligence, Natural language processing, Machine learning, Speech recognition, Engineering, Mechanical engineering, Materials science, Composite material, Paleontology, BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
26Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 7, 2024: 16, 2023: 3Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4386908184 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2309.10668 |
| ids.doi | https://doi.org/10.48550/arxiv.2309.10668 |
| ids.openalex | https://openalex.org/W4386908184 |
| fwci | |
| type | preprint |
| title | Language Modeling Is Compression |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10181 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9965000152587891 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Natural Language Processing Techniques |
| topics[1].id | https://openalex.org/T10028 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9947999715805054 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Topic Modeling |
| topics[2].id | https://openalex.org/T10201 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9781000018119812 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C81081738 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8020728826522827 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q55542 |
| concepts[0].display_name | Lossless compression |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7609828114509583 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C165021410 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6327642798423767 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q55564 |
| concepts[2].display_name | Lossy compression |
| concepts[3].id | https://openalex.org/C137293760 |
| concepts[3].level | 2 |
| concepts[3].score | 0.616269588470459 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3621696 |
| concepts[3].display_name | Language model |
| concepts[4].id | https://openalex.org/C131097465 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5732207298278809 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q178898 |
| concepts[4].display_name | Gas compressor |
| concepts[5].id | https://openalex.org/C180016635 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5218861699104309 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2712821 |
| concepts[5].display_name | Compression (physics) |
| concepts[6].id | https://openalex.org/C2779343474 |
| concepts[6].level | 2 |
| concepts[6].score | 0.49215835332870483 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[6].display_name | Context (archaeology) |
| concepts[7].id | https://openalex.org/C78548338 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4433095157146454 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q2493 |
| concepts[7].display_name | Data compression |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.41613057255744934 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C204321447 |
| concepts[9].level | 1 |
| concepts[9].score | 0.41087862849235535 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[9].display_name | Natural language processing |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.39920559525489807 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C28490314 |
| concepts[11].level | 1 |
| concepts[11].score | 0.3451943099498749 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[11].display_name | Speech recognition |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.1138153076171875 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| concepts[13].id | https://openalex.org/C78519656 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q101333 |
| concepts[13].display_name | Mechanical engineering |
| concepts[14].id | https://openalex.org/C192562407 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[14].display_name | Materials science |
| concepts[15].id | https://openalex.org/C159985019 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[15].display_name | Composite material |
| concepts[16].id | https://openalex.org/C151730666 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[16].display_name | Paleontology |
| concepts[17].id | https://openalex.org/C86803240 |
| concepts[17].level | 0 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[17].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/lossless-compression |
| keywords[0].score | 0.8020728826522827 |
| keywords[0].display_name | Lossless compression |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7609828114509583 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/lossy-compression |
| keywords[2].score | 0.6327642798423767 |
| keywords[2].display_name | Lossy compression |
| keywords[3].id | https://openalex.org/keywords/language-model |
| keywords[3].score | 0.616269588470459 |
| keywords[3].display_name | Language model |
| keywords[4].id | https://openalex.org/keywords/gas-compressor |
| keywords[4].score | 0.5732207298278809 |
| keywords[4].display_name | Gas compressor |
| keywords[5].id | https://openalex.org/keywords/compression |
| keywords[5].score | 0.5218861699104309 |
| keywords[5].display_name | Compression (physics) |
| keywords[6].id | https://openalex.org/keywords/context |
| keywords[6].score | 0.49215835332870483 |
| keywords[6].display_name | Context (archaeology) |
| keywords[7].id | https://openalex.org/keywords/data-compression |
| keywords[7].score | 0.4433095157146454 |
| keywords[7].display_name | Data compression |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.41613057255744934 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/natural-language-processing |
| keywords[9].score | 0.41087862849235535 |
| keywords[9].display_name | Natural language processing |
| keywords[10].id | https://openalex.org/keywords/machine-learning |
| keywords[10].score | 0.39920559525489807 |
| keywords[10].display_name | Machine learning |
| keywords[11].id | https://openalex.org/keywords/speech-recognition |
| keywords[11].score | 0.3451943099498749 |
| keywords[11].display_name | Speech recognition |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.1138153076171875 |
| keywords[12].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2309.10668 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2309.10668 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2309.10668 |
| locations[1].id | doi:10.48550/arxiv.2309.10668 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2309.10668 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5059962909 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Grégoire Delétang |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Delétang, Grégoire |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5077124139 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-8616-2558 |
| authorships[1].author.display_name | Anian Ruoss |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ruoss, Anian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5059582849 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Paul-Ambroise Duquenne |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Duquenne, Paul-Ambroise |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5020795308 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-9411-927X |
| authorships[3].author.display_name | Elliot Catt |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Catt, Elliot |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5013602545 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-8039-4027 |
| authorships[4].author.display_name | Tim Genewein |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Genewein, Tim |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5088656569 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Christopher Mattern |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Mattern, Christopher |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5026686188 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Jordi Grau-Moya |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Grau-Moya, Jordi |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5017305728 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-7090-3078 |
| authorships[7].author.display_name | Li Kevin Wenliang |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Wenliang, Li Kevin |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5005322233 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Matthew Aitchison |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Aitchison, Matthew |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5110938957 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Laurent Orseau |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Orseau, Laurent |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5073944062 |
| authorships[10].author.orcid | https://orcid.org/0000-0002-3263-4097 |
| authorships[10].author.display_name | Marcus Hütter |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Hutter, Marcus |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5060709021 |
| authorships[11].author.orcid | |
| authorships[11].author.display_name | Joel Veness |
| authorships[11].author_position | last |
| authorships[11].raw_author_name | Veness, Joel |
| authorships[11].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2309.10668 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Language Modeling Is Compression |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10181 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9965000152587891 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Natural Language Processing Techniques |
| related_works | https://openalex.org/W2385628723, https://openalex.org/W2547124190, https://openalex.org/W3180760233, https://openalex.org/W3035703949, https://openalex.org/W4247601675, https://openalex.org/W1970394887, https://openalex.org/W755971114, https://openalex.org/W2118338613, https://openalex.org/W1982468865, https://openalex.org/W4313046148 |
| cited_by_count | 26 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 7 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 16 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 3 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2309.10668 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2309.10668 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2309.10668 |
| primary_location.id | pmh:oai:arXiv.org:2309.10668 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2309.10668 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2309.10668 |
| publication_date | 2023-09-19 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 151 |
| abstract_inverted_index.In | 52 |
| abstract_inverted_index.It | 0 |
| abstract_inverted_index.We | 76 |
| abstract_inverted_index.be | 9, 49 |
| abstract_inverted_index.in | 18 |
| abstract_inverted_index.of | 65, 72, 120 |
| abstract_inverted_index.on | 27, 108 |
| abstract_inverted_index.or | 130 |
| abstract_inverted_index.to | 48, 113, 118, 143, 149 |
| abstract_inverted_index.us | 142 |
| abstract_inverted_index.we | 55, 135 |
| abstract_inverted_index.For | 101 |
| abstract_inverted_index.PNG | 128 |
| abstract_inverted_index.and | 14, 31, 67, 86, 98, 115 |
| abstract_inverted_index.any | 145 |
| abstract_inverted_index.are | 46, 82 |
| abstract_inverted_index.can | 8 |
| abstract_inverted_index.for | 57 |
| abstract_inverted_index.has | 1, 25 |
| abstract_inverted_index.raw | 122 |
| abstract_inverted_index.the | 21, 59, 63, 69, 88, 138 |
| abstract_inverted_index.use | 144 |
| abstract_inverted_index.70B, | 104 |
| abstract_inverted_index.FLAC | 131 |
| abstract_inverted_index.been | 3 |
| abstract_inverted_index.into | 11, 94 |
| abstract_inverted_index.lens | 64 |
| abstract_inverted_index.like | 127 |
| abstract_inverted_index.long | 2 |
| abstract_inverted_index.show | 77, 136 |
| abstract_inverted_index.that | 5, 78, 87, 137 |
| abstract_inverted_index.they | 45 |
| abstract_inverted_index.this | 53 |
| abstract_inverted_index.vice | 15 |
| abstract_inverted_index.(like | 147 |
| abstract_inverted_index.16.4% | 119 |
| abstract_inverted_index.43.4% | 114 |
| abstract_inverted_index.Since | 36 |
| abstract_inverted_index.build | 150 |
| abstract_inverted_index.gzip) | 148 |
| abstract_inverted_index.large | 30, 38, 73, 79 |
| abstract_inverted_index.laws, | 96 |
| abstract_inverted_index.novel | 92 |
| abstract_inverted_index.size, | 123 |
| abstract_inverted_index.text, | 109 |
| abstract_inverted_index.their | 121 |
| abstract_inverted_index.these | 37 |
| abstract_inverted_index.while | 105 |
| abstract_inverted_index.work, | 54 |
| abstract_inverted_index.allows | 141 |
| abstract_inverted_index.model. | 154 |
| abstract_inverted_index.models | 7, 40, 81 |
| abstract_inverted_index.recent | 19 |
| abstract_inverted_index.strong | 50 |
| abstract_inverted_index.versa. | 16 |
| abstract_inverted_index.years, | 20 |
| abstract_inverted_index.(58.5%) | 129 |
| abstract_inverted_index.beating | 124 |
| abstract_inverted_index.exhibit | 41 |
| abstract_inverted_index.focused | 26 |
| abstract_inverted_index.machine | 22 |
| abstract_inverted_index.models. | 35, 75 |
| abstract_inverted_index.patches | 112 |
| abstract_inverted_index.problem | 61 |
| abstract_inverted_index.samples | 117 |
| abstract_inverted_index.scaling | 95 |
| abstract_inverted_index.through | 62 |
| abstract_inverted_index.trained | 106 |
| abstract_inverted_index.viewing | 58 |
| abstract_inverted_index.(30.3%), | 132 |
| abstract_inverted_index.Finally, | 134 |
| abstract_inverted_index.ImageNet | 111 |
| abstract_inverted_index.advocate | 56 |
| abstract_inverted_index.evaluate | 68 |
| abstract_inverted_index.example, | 102 |
| abstract_inverted_index.insights | 93 |
| abstract_inverted_index.language | 39, 80 |
| abstract_inverted_index.learning | 23 |
| abstract_inverted_index.lossless | 12 |
| abstract_inverted_index.powerful | 32, 83 |
| abstract_inverted_index.provides | 91 |
| abstract_inverted_index.training | 28 |
| abstract_inverted_index.community | 24 |
| abstract_inverted_index.learning. | 100 |
| abstract_inverted_index.primarily | 107 |
| abstract_inverted_index.viewpoint | 90 |
| abstract_inverted_index.(language) | 34 |
| abstract_inverted_index.Chinchilla | 103 |
| abstract_inverted_index.compresses | 110 |
| abstract_inverted_index.compressor | 146 |
| abstract_inverted_index.generative | 153 |
| abstract_inverted_index.impressive | 42 |
| abstract_inverted_index.in-context | 99 |
| abstract_inverted_index.prediction | 60 |
| abstract_inverted_index.predictive | 6, 43 |
| abstract_inverted_index.predictors | 85 |
| abstract_inverted_index.LibriSpeech | 116 |
| abstract_inverted_index.compression | 66, 70, 89 |
| abstract_inverted_index.compressors | 13, 126 |
| abstract_inverted_index.conditional | 152 |
| abstract_inverted_index.equivalence | 140 |
| abstract_inverted_index.established | 4 |
| abstract_inverted_index.transformed | 10 |
| abstract_inverted_index.(foundation) | 74 |
| abstract_inverted_index.capabilities | 71 |
| abstract_inverted_index.compressors. | 51 |
| abstract_inverted_index.increasingly | 29 |
| abstract_inverted_index.Incidentally, | 17 |
| abstract_inverted_index.capabilities, | 44 |
| abstract_inverted_index.respectively. | 133 |
| abstract_inverted_index.tokenization, | 97 |
| abstract_inverted_index.domain-specific | 125 |
| abstract_inverted_index.general-purpose | 84 |
| abstract_inverted_index.self-supervised | 33 |
| abstract_inverted_index.well-positioned | 47 |
| abstract_inverted_index.prediction-compression | 139 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 12 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.8199999928474426 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |