Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens Article Swipe
Zhanpeng Zeng
,
Cole Hawkins
,
Mingyi Hong
,
Aston Zhang
,
Nikolaos Pappas
,
Vikas Singh
,
Shuai Zheng
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.04241
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2305.04241
Transformers are central in modern natural language processing and computer vision applications. Despite recent works devoted to reducing the quadratic cost of such models (as a function of the sequence length), dealing with ultra long sequences (e.g., with more than 16K tokens) remains challenging. Applications such as answering questions based on a book or summarizing a scientific article are inefficient or infeasible. Here, we propose to significantly improve the efficiency of Transformers for ultra long sequences, by compressing the sequence into a much smaller representation at each layer. Specifically, by exploiting the fact that in many tasks, only a small subset of special tokens (we call VIP-tokens) are most relevant to the final prediction, we propose a VIP-token centric compression (VCC) scheme which selectively compresses the sequence based on their impact on approximating the representation of the VIP-tokens. Compared with competitive baselines, our algorithm is not only efficient (achieving more than $3\times$ efficiency gain compared to baselines on 4K and 16K lengths), but also offers competitive/better performance on a large number of tasks. Further, we show that our algorithm scales to 128K tokens (or more) while consistently offering accuracy improvement.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2305.04241
- https://arxiv.org/pdf/2305.04241
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4375958396
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4375958396Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2305.04241Digital Object Identifier
- Title
-
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important TokensWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-05-07Full publication date if available
- Authors
-
Zhanpeng Zeng, Cole Hawkins, Mingyi Hong, Aston Zhang, Nikolaos Pappas, Vikas Singh, Shuai ZhengList of authors in order
- Landing page
-
https://arxiv.org/abs/2305.04241Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2305.04241Direct 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/2305.04241Direct OA link when available
- Concepts
-
Security token, Computer science, Transformer, Sequence (biology), Quadratic equation, Representation (politics), Theoretical computer science, Algorithm, Mathematics, Computer network, Voltage, Genetics, Physics, Law, Quantum mechanics, Biology, Geometry, Politics, Political scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2023: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4375958396 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2305.04241 |
| ids.doi | https://doi.org/10.48550/arxiv.2305.04241 |
| ids.openalex | https://openalex.org/W4375958396 |
| fwci | |
| type | preprint |
| title | Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11269 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9945999979972839 |
| 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 | Algorithms and Data Compression |
| topics[1].id | https://openalex.org/T10627 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9904000163078308 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Image and Video Retrieval Techniques |
| topics[2].id | https://openalex.org/T12254 |
| topics[2].field.id | https://openalex.org/fields/13 |
| topics[2].field.display_name | Biochemistry, Genetics and Molecular Biology |
| topics[2].score | 0.9837999939918518 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1312 |
| topics[2].subfield.display_name | Molecular Biology |
| topics[2].display_name | Machine Learning in Bioinformatics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C48145219 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8201830983161926 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1335365 |
| concepts[0].display_name | Security token |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8053388595581055 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C66322947 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6750127077102661 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[2].display_name | Transformer |
| concepts[3].id | https://openalex.org/C2778112365 |
| concepts[3].level | 2 |
| concepts[3].score | 0.45647862553596497 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q3511065 |
| concepts[3].display_name | Sequence (biology) |
| concepts[4].id | https://openalex.org/C129844170 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4348779618740082 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q41299 |
| concepts[4].display_name | Quadratic equation |
| concepts[5].id | https://openalex.org/C2776359362 |
| concepts[5].level | 3 |
| concepts[5].score | 0.42881375551223755 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[5].display_name | Representation (politics) |
| concepts[6].id | https://openalex.org/C80444323 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3782549798488617 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[6].display_name | Theoretical computer science |
| concepts[7].id | https://openalex.org/C11413529 |
| concepts[7].level | 1 |
| concepts[7].score | 0.34070688486099243 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[7].display_name | Algorithm |
| concepts[8].id | https://openalex.org/C33923547 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0790315568447113 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[8].display_name | Mathematics |
| concepts[9].id | https://openalex.org/C31258907 |
| concepts[9].level | 1 |
| concepts[9].score | 0.07772496342658997 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[9].display_name | Computer network |
| concepts[10].id | https://openalex.org/C165801399 |
| concepts[10].level | 2 |
| concepts[10].score | 0.06934326887130737 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[10].display_name | Voltage |
| concepts[11].id | https://openalex.org/C54355233 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7162 |
| concepts[11].display_name | Genetics |
| concepts[12].id | https://openalex.org/C121332964 |
| concepts[12].level | 0 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[12].display_name | Physics |
| concepts[13].id | https://openalex.org/C199539241 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[13].display_name | Law |
| concepts[14].id | https://openalex.org/C62520636 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[14].display_name | Quantum mechanics |
| concepts[15].id | https://openalex.org/C86803240 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[15].display_name | Biology |
| concepts[16].id | https://openalex.org/C2524010 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[16].display_name | Geometry |
| concepts[17].id | https://openalex.org/C94625758 |
| concepts[17].level | 2 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[17].display_name | Politics |
| concepts[18].id | https://openalex.org/C17744445 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[18].display_name | Political science |
| keywords[0].id | https://openalex.org/keywords/security-token |
| keywords[0].score | 0.8201830983161926 |
| keywords[0].display_name | Security token |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8053388595581055 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/transformer |
| keywords[2].score | 0.6750127077102661 |
| keywords[2].display_name | Transformer |
| keywords[3].id | https://openalex.org/keywords/sequence |
| keywords[3].score | 0.45647862553596497 |
| keywords[3].display_name | Sequence (biology) |
| keywords[4].id | https://openalex.org/keywords/quadratic-equation |
| keywords[4].score | 0.4348779618740082 |
| keywords[4].display_name | Quadratic equation |
| keywords[5].id | https://openalex.org/keywords/representation |
| keywords[5].score | 0.42881375551223755 |
| keywords[5].display_name | Representation (politics) |
| keywords[6].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[6].score | 0.3782549798488617 |
| keywords[6].display_name | Theoretical computer science |
| keywords[7].id | https://openalex.org/keywords/algorithm |
| keywords[7].score | 0.34070688486099243 |
| keywords[7].display_name | Algorithm |
| keywords[8].id | https://openalex.org/keywords/mathematics |
| keywords[8].score | 0.0790315568447113 |
| keywords[8].display_name | Mathematics |
| keywords[9].id | https://openalex.org/keywords/computer-network |
| keywords[9].score | 0.07772496342658997 |
| keywords[9].display_name | Computer network |
| keywords[10].id | https://openalex.org/keywords/voltage |
| keywords[10].score | 0.06934326887130737 |
| keywords[10].display_name | Voltage |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2305.04241 |
| 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/2305.04241 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2305.04241 |
| locations[1].id | doi:10.48550/arxiv.2305.04241 |
| 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.2305.04241 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5031839366 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Zhanpeng Zeng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zeng, Zhanpeng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5070161118 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Cole Hawkins |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hawkins, Cole |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100633783 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1263-9365 |
| authorships[2].author.display_name | Mingyi Hong |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Hong, Mingyi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5049841140 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Aston Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Aston |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5023518080 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2004-8111 |
| authorships[4].author.display_name | Nikolaos Pappas |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Pappas, Nikolaos |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100779003 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-8355-6519 |
| authorships[5].author.display_name | Vikas Singh |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Singh, Vikas |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5100726973 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-1636-631X |
| authorships[6].author.display_name | Shuai Zheng |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Zheng, Shuai |
| authorships[6].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/2305.04241 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11269 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9945999979972839 |
| 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 | Algorithms and Data Compression |
| related_works | https://openalex.org/W4388335561, https://openalex.org/W2970530566, https://openalex.org/W4288261899, https://openalex.org/W4307309205, https://openalex.org/W2967478618, https://openalex.org/W4385009901, https://openalex.org/W4385572700, https://openalex.org/W2997152889, https://openalex.org/W4387768015, https://openalex.org/W3016124757 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2023 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2305.04241 |
| 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/2305.04241 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2305.04241 |
| primary_location.id | pmh:oai:arXiv.org:2305.04241 |
| 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/2305.04241 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2305.04241 |
| publication_date | 2023-05-07 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 25, 51, 55, 81, 98, 116, 168 |
| abstract_inverted_index.4K | 158 |
| abstract_inverted_index.as | 46 |
| abstract_inverted_index.at | 85 |
| abstract_inverted_index.by | 76, 89 |
| abstract_inverted_index.in | 3, 94 |
| abstract_inverted_index.is | 144 |
| abstract_inverted_index.of | 21, 27, 70, 101, 135, 171 |
| abstract_inverted_index.on | 50, 128, 131, 157, 167 |
| abstract_inverted_index.or | 53, 60 |
| abstract_inverted_index.to | 16, 65, 110, 155, 180 |
| abstract_inverted_index.we | 63, 114, 174 |
| abstract_inverted_index.(as | 24 |
| abstract_inverted_index.(or | 183 |
| abstract_inverted_index.(we | 104 |
| abstract_inverted_index.16K | 40, 160 |
| abstract_inverted_index.and | 8, 159 |
| abstract_inverted_index.are | 1, 58, 107 |
| abstract_inverted_index.but | 162 |
| abstract_inverted_index.for | 72 |
| abstract_inverted_index.not | 145 |
| abstract_inverted_index.our | 142, 177 |
| abstract_inverted_index.the | 18, 28, 68, 78, 91, 111, 125, 133, 136 |
| abstract_inverted_index.128K | 181 |
| abstract_inverted_index.also | 163 |
| abstract_inverted_index.book | 52 |
| abstract_inverted_index.call | 105 |
| abstract_inverted_index.cost | 20 |
| abstract_inverted_index.each | 86 |
| abstract_inverted_index.fact | 92 |
| abstract_inverted_index.gain | 153 |
| abstract_inverted_index.into | 80 |
| abstract_inverted_index.long | 34, 74 |
| abstract_inverted_index.many | 95 |
| abstract_inverted_index.more | 38, 149 |
| abstract_inverted_index.most | 108 |
| abstract_inverted_index.much | 82 |
| abstract_inverted_index.only | 97, 146 |
| abstract_inverted_index.show | 175 |
| abstract_inverted_index.such | 22, 45 |
| abstract_inverted_index.than | 39, 150 |
| abstract_inverted_index.that | 93, 176 |
| abstract_inverted_index.with | 32, 37, 139 |
| abstract_inverted_index.(VCC) | 120 |
| abstract_inverted_index.Here, | 62 |
| abstract_inverted_index.based | 49, 127 |
| abstract_inverted_index.final | 112 |
| abstract_inverted_index.large | 169 |
| abstract_inverted_index.more) | 184 |
| abstract_inverted_index.small | 99 |
| abstract_inverted_index.their | 129 |
| abstract_inverted_index.ultra | 33, 73 |
| abstract_inverted_index.which | 122 |
| abstract_inverted_index.while | 185 |
| abstract_inverted_index.works | 14 |
| abstract_inverted_index.(e.g., | 36 |
| abstract_inverted_index.impact | 130 |
| abstract_inverted_index.layer. | 87 |
| abstract_inverted_index.models | 23 |
| abstract_inverted_index.modern | 4 |
| abstract_inverted_index.number | 170 |
| abstract_inverted_index.offers | 164 |
| abstract_inverted_index.recent | 13 |
| abstract_inverted_index.scales | 179 |
| abstract_inverted_index.scheme | 121 |
| abstract_inverted_index.subset | 100 |
| abstract_inverted_index.tasks, | 96 |
| abstract_inverted_index.tasks. | 172 |
| abstract_inverted_index.tokens | 103, 182 |
| abstract_inverted_index.vision | 10 |
| abstract_inverted_index.Despite | 12 |
| abstract_inverted_index.article | 57 |
| abstract_inverted_index.central | 2 |
| abstract_inverted_index.centric | 118 |
| abstract_inverted_index.dealing | 31 |
| abstract_inverted_index.devoted | 15 |
| abstract_inverted_index.improve | 67 |
| abstract_inverted_index.natural | 5 |
| abstract_inverted_index.propose | 64, 115 |
| abstract_inverted_index.remains | 42 |
| abstract_inverted_index.smaller | 83 |
| abstract_inverted_index.special | 102 |
| abstract_inverted_index.tokens) | 41 |
| abstract_inverted_index.Compared | 138 |
| abstract_inverted_index.Further, | 173 |
| abstract_inverted_index.accuracy | 188 |
| abstract_inverted_index.compared | 154 |
| abstract_inverted_index.computer | 9 |
| abstract_inverted_index.function | 26 |
| abstract_inverted_index.language | 6 |
| abstract_inverted_index.length), | 30 |
| abstract_inverted_index.offering | 187 |
| abstract_inverted_index.reducing | 17 |
| abstract_inverted_index.relevant | 109 |
| abstract_inverted_index.sequence | 29, 79, 126 |
| abstract_inverted_index.$3\times$ | 151 |
| abstract_inverted_index.VIP-token | 117 |
| abstract_inverted_index.algorithm | 143, 178 |
| abstract_inverted_index.answering | 47 |
| abstract_inverted_index.baselines | 156 |
| abstract_inverted_index.efficient | 147 |
| abstract_inverted_index.lengths), | 161 |
| abstract_inverted_index.quadratic | 19 |
| abstract_inverted_index.questions | 48 |
| abstract_inverted_index.sequences | 35 |
| abstract_inverted_index.(achieving | 148 |
| abstract_inverted_index.baselines, | 141 |
| abstract_inverted_index.compresses | 124 |
| abstract_inverted_index.efficiency | 69, 152 |
| abstract_inverted_index.exploiting | 90 |
| abstract_inverted_index.processing | 7 |
| abstract_inverted_index.scientific | 56 |
| abstract_inverted_index.sequences, | 75 |
| abstract_inverted_index.VIP-tokens) | 106 |
| abstract_inverted_index.VIP-tokens. | 137 |
| abstract_inverted_index.competitive | 140 |
| abstract_inverted_index.compressing | 77 |
| abstract_inverted_index.compression | 119 |
| abstract_inverted_index.inefficient | 59 |
| abstract_inverted_index.infeasible. | 61 |
| abstract_inverted_index.performance | 166 |
| abstract_inverted_index.prediction, | 113 |
| abstract_inverted_index.selectively | 123 |
| abstract_inverted_index.summarizing | 54 |
| abstract_inverted_index.Applications | 44 |
| abstract_inverted_index.Transformers | 0, 71 |
| abstract_inverted_index.challenging. | 43 |
| abstract_inverted_index.consistently | 186 |
| abstract_inverted_index.improvement. | 189 |
| abstract_inverted_index.Specifically, | 88 |
| abstract_inverted_index.applications. | 11 |
| abstract_inverted_index.approximating | 132 |
| abstract_inverted_index.significantly | 66 |
| abstract_inverted_index.representation | 84, 134 |
| abstract_inverted_index.competitive/better | 165 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |