Adaptivity and Modularity for Efficient Generalization Over Task Complexity Article Swipe
Samira Abnar
,
Omid Saremi
,
Laurent Dinh
,
Shantel Wilson
,
Miguel Ángel Bautista
,
Chen Huang
,
Vimal Thilak
,
Etai Littwin
,
Jiatao Gu
,
Josh Susskind
,
Samy Bengio
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.08866
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.08866
Can transformers generalize efficiently on problems that require dealing with examples with different levels of difficulty? We introduce a new task tailored to assess generalization over different complexities and present results that indicate that standard transformers face challenges in solving these tasks. These tasks are variations of pointer value retrieval previously introduced by Zhang et al. (2021). We investigate how the use of a mechanism for adaptive and modular computation in transformers facilitates the learning of tasks that demand generalization over the number of sequential computation steps (i.e., the depth of the computation graph). Based on our observations, we propose a transformer-based architecture called Hyper-UT, which combines dynamic function generation from hyper networks with adaptive depth from Universal Transformers. This model demonstrates higher accuracy and a fairer allocation of computational resources when generalizing to higher numbers of computation steps. We conclude that mechanisms for adaptive depth and modularity complement each other in improving efficient generalization concerning example complexity. Additionally, to emphasize the broad applicability of our findings, we illustrate that in a standard image recognition task, Hyper- UT's performance matches that of a ViT model but with considerably reduced computational demands (achieving over 70\% average savings by effectively using fewer layers).
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.08866
- https://arxiv.org/pdf/2310.08866
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387687193
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387687193Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.08866Digital Object Identifier
- Title
-
Adaptivity and Modularity for Efficient Generalization Over Task ComplexityWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-13Full publication date if available
- Authors
-
Samira Abnar, Omid Saremi, Laurent Dinh, Shantel Wilson, Miguel Ángel Bautista, Chen Huang, Vimal Thilak, Etai Littwin, Jiatao Gu, Josh Susskind, Samy BengioList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.08866Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.08866Direct 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/2310.08866Direct OA link when available
- Concepts
-
Computer science, Computation, Modular design, Transformer, Pointer (user interface), Theoretical computer science, Generalization, Artificial intelligence, Computational complexity theory, Machine learning, Algorithm, Mathematics, Programming language, Mathematical analysis, Quantum mechanics, Physics, VoltageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4387687193 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.08866 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.08866 |
| ids.openalex | https://openalex.org/W4387687193 |
| fwci | |
| type | preprint |
| title | Adaptivity and Modularity for Efficient Generalization Over Task Complexity |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12535 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9922000169754028 |
| 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 | Machine Learning and Data Classification |
| topics[1].id | https://openalex.org/T11307 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9768999814987183 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[2].id | https://openalex.org/T11714 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9240999817848206 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7227800488471985 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C45374587 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7046966552734375 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[1].display_name | Computation |
| concepts[2].id | https://openalex.org/C101468663 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6251764297485352 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1620158 |
| concepts[2].display_name | Modular design |
| concepts[3].id | https://openalex.org/C66322947 |
| concepts[3].level | 3 |
| concepts[3].score | 0.5874663591384888 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11658 |
| concepts[3].display_name | Transformer |
| concepts[4].id | https://openalex.org/C150202949 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5401251912117004 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q107602 |
| concepts[4].display_name | Pointer (user interface) |
| concepts[5].id | https://openalex.org/C80444323 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5212712287902832 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[5].display_name | Theoretical computer science |
| concepts[6].id | https://openalex.org/C177148314 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4826377034187317 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q170084 |
| concepts[6].display_name | Generalization |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.44370776414871216 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C179799912 |
| concepts[8].level | 2 |
| concepts[8].score | 0.43228596448898315 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q205084 |
| concepts[8].display_name | Computational complexity theory |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.33714431524276733 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3097801208496094 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.14850294589996338 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C199360897 |
| concepts[12].level | 1 |
| concepts[12].score | 0.07975795865058899 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[12].display_name | Programming language |
| concepts[13].id | https://openalex.org/C134306372 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[13].display_name | Mathematical analysis |
| 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/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C165801399 |
| concepts[16].level | 2 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q25428 |
| concepts[16].display_name | Voltage |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7227800488471985 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/computation |
| keywords[1].score | 0.7046966552734375 |
| keywords[1].display_name | Computation |
| keywords[2].id | https://openalex.org/keywords/modular-design |
| keywords[2].score | 0.6251764297485352 |
| keywords[2].display_name | Modular design |
| keywords[3].id | https://openalex.org/keywords/transformer |
| keywords[3].score | 0.5874663591384888 |
| keywords[3].display_name | Transformer |
| keywords[4].id | https://openalex.org/keywords/pointer |
| keywords[4].score | 0.5401251912117004 |
| keywords[4].display_name | Pointer (user interface) |
| keywords[5].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[5].score | 0.5212712287902832 |
| keywords[5].display_name | Theoretical computer science |
| keywords[6].id | https://openalex.org/keywords/generalization |
| keywords[6].score | 0.4826377034187317 |
| keywords[6].display_name | Generalization |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.44370776414871216 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/computational-complexity-theory |
| keywords[8].score | 0.43228596448898315 |
| keywords[8].display_name | Computational complexity theory |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.33714431524276733 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.3097801208496094 |
| keywords[10].display_name | Algorithm |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.14850294589996338 |
| keywords[11].display_name | Mathematics |
| keywords[12].id | https://openalex.org/keywords/programming-language |
| keywords[12].score | 0.07975795865058899 |
| keywords[12].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.08866 |
| 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/2310.08866 |
| 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/2310.08866 |
| locations[1].id | doi:10.48550/arxiv.2310.08866 |
| 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 | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| 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.2310.08866 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5084377683 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Samira Abnar |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Abnar, Samira |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5011650393 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-6718-093X |
| authorships[1].author.display_name | Omid Saremi |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Saremi, Omid |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5113871902 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Laurent Dinh |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Dinh, Laurent |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100886814 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Shantel Wilson |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wilson, Shantel |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5011106959 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Miguel Ángel Bautista |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Bautista, Miguel Angel |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100606858 |
| authorships[5].author.orcid | https://orcid.org/0009-0005-0654-5081 |
| authorships[5].author.display_name | Chen Huang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Huang, Chen |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5059333418 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Vimal Thilak |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Thilak, Vimal |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5049929304 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Etai Littwin |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Littwin, Etai |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5112542984 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Jiatao Gu |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Gu, Jiatao |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5043808400 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Josh Susskind |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Susskind, Josh |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5017529415 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Samy Bengio |
| authorships[10].author_position | last |
| authorships[10].raw_author_name | Bengio, Samy |
| authorships[10].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/2310.08866 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Adaptivity and Modularity for Efficient Generalization Over Task Complexity |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12535 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9922000169754028 |
| 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 | Machine Learning and Data Classification |
| related_works | https://openalex.org/W3162204513, https://openalex.org/W2387387477, https://openalex.org/W2394051415, https://openalex.org/W4255928847, https://openalex.org/W2378076731, https://openalex.org/W4388218401, https://openalex.org/W2371138613, https://openalex.org/W4286888643, https://openalex.org/W2352114091, https://openalex.org/W2048963458 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.08866 |
| 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/2310.08866 |
| 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/2310.08866 |
| primary_location.id | pmh:oai:arXiv.org:2310.08866 |
| 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/2310.08866 |
| 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/2310.08866 |
| publication_date | 2023-10-13 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 18, 63, 100, 125, 171, 182 |
| abstract_inverted_index.We | 16, 57, 139 |
| abstract_inverted_index.by | 52, 196 |
| abstract_inverted_index.et | 54 |
| abstract_inverted_index.in | 38, 70, 151, 170 |
| abstract_inverted_index.of | 14, 46, 62, 75, 83, 90, 128, 136, 164, 181 |
| abstract_inverted_index.on | 4, 95 |
| abstract_inverted_index.to | 22, 133, 159 |
| abstract_inverted_index.we | 98, 167 |
| abstract_inverted_index.Can | 0 |
| abstract_inverted_index.ViT | 183 |
| abstract_inverted_index.al. | 55 |
| abstract_inverted_index.and | 28, 67, 124, 146 |
| abstract_inverted_index.are | 44 |
| abstract_inverted_index.but | 185 |
| abstract_inverted_index.for | 65, 143 |
| abstract_inverted_index.how | 59 |
| abstract_inverted_index.new | 19 |
| abstract_inverted_index.our | 96, 165 |
| abstract_inverted_index.the | 60, 73, 81, 88, 91, 161 |
| abstract_inverted_index.use | 61 |
| abstract_inverted_index.70\% | 193 |
| abstract_inverted_index.This | 119 |
| abstract_inverted_index.UT's | 177 |
| abstract_inverted_index.each | 149 |
| abstract_inverted_index.face | 36 |
| abstract_inverted_index.from | 110, 116 |
| abstract_inverted_index.over | 25, 80, 192 |
| abstract_inverted_index.task | 20 |
| abstract_inverted_index.that | 6, 31, 33, 77, 141, 169, 180 |
| abstract_inverted_index.when | 131 |
| abstract_inverted_index.with | 9, 11, 113, 186 |
| abstract_inverted_index.Based | 94 |
| abstract_inverted_index.These | 42 |
| abstract_inverted_index.Zhang | 53 |
| abstract_inverted_index.broad | 162 |
| abstract_inverted_index.depth | 89, 115, 145 |
| abstract_inverted_index.fewer | 199 |
| abstract_inverted_index.hyper | 111 |
| abstract_inverted_index.image | 173 |
| abstract_inverted_index.model | 120, 184 |
| abstract_inverted_index.other | 150 |
| abstract_inverted_index.steps | 86 |
| abstract_inverted_index.task, | 175 |
| abstract_inverted_index.tasks | 43, 76 |
| abstract_inverted_index.these | 40 |
| abstract_inverted_index.using | 198 |
| abstract_inverted_index.value | 48 |
| abstract_inverted_index.which | 105 |
| abstract_inverted_index.(i.e., | 87 |
| abstract_inverted_index.Hyper- | 176 |
| abstract_inverted_index.assess | 23 |
| abstract_inverted_index.called | 103 |
| abstract_inverted_index.demand | 78 |
| abstract_inverted_index.fairer | 126 |
| abstract_inverted_index.higher | 122, 134 |
| abstract_inverted_index.levels | 13 |
| abstract_inverted_index.number | 82 |
| abstract_inverted_index.steps. | 138 |
| abstract_inverted_index.tasks. | 41 |
| abstract_inverted_index.(2021). | 56 |
| abstract_inverted_index.average | 194 |
| abstract_inverted_index.dealing | 8 |
| abstract_inverted_index.demands | 190 |
| abstract_inverted_index.dynamic | 107 |
| abstract_inverted_index.example | 156 |
| abstract_inverted_index.graph). | 93 |
| abstract_inverted_index.matches | 179 |
| abstract_inverted_index.modular | 68 |
| abstract_inverted_index.numbers | 135 |
| abstract_inverted_index.pointer | 47 |
| abstract_inverted_index.present | 29 |
| abstract_inverted_index.propose | 99 |
| abstract_inverted_index.reduced | 188 |
| abstract_inverted_index.require | 7 |
| abstract_inverted_index.results | 30 |
| abstract_inverted_index.savings | 195 |
| abstract_inverted_index.solving | 39 |
| abstract_inverted_index.accuracy | 123 |
| abstract_inverted_index.adaptive | 66, 114, 144 |
| abstract_inverted_index.combines | 106 |
| abstract_inverted_index.conclude | 140 |
| abstract_inverted_index.examples | 10 |
| abstract_inverted_index.function | 108 |
| abstract_inverted_index.indicate | 32 |
| abstract_inverted_index.layers). | 200 |
| abstract_inverted_index.learning | 74 |
| abstract_inverted_index.networks | 112 |
| abstract_inverted_index.problems | 5 |
| abstract_inverted_index.standard | 34, 172 |
| abstract_inverted_index.tailored | 21 |
| abstract_inverted_index.Hyper-UT, | 104 |
| abstract_inverted_index.Universal | 117 |
| abstract_inverted_index.different | 12, 26 |
| abstract_inverted_index.efficient | 153 |
| abstract_inverted_index.emphasize | 160 |
| abstract_inverted_index.findings, | 166 |
| abstract_inverted_index.improving | 152 |
| abstract_inverted_index.introduce | 17 |
| abstract_inverted_index.mechanism | 64 |
| abstract_inverted_index.resources | 130 |
| abstract_inverted_index.retrieval | 49 |
| abstract_inverted_index.(achieving | 191 |
| abstract_inverted_index.allocation | 127 |
| abstract_inverted_index.challenges | 37 |
| abstract_inverted_index.complement | 148 |
| abstract_inverted_index.concerning | 155 |
| abstract_inverted_index.generalize | 2 |
| abstract_inverted_index.generation | 109 |
| abstract_inverted_index.illustrate | 168 |
| abstract_inverted_index.introduced | 51 |
| abstract_inverted_index.mechanisms | 142 |
| abstract_inverted_index.modularity | 147 |
| abstract_inverted_index.previously | 50 |
| abstract_inverted_index.sequential | 84 |
| abstract_inverted_index.variations | 45 |
| abstract_inverted_index.complexity. | 157 |
| abstract_inverted_index.computation | 69, 85, 92, 137 |
| abstract_inverted_index.difficulty? | 15 |
| abstract_inverted_index.effectively | 197 |
| abstract_inverted_index.efficiently | 3 |
| abstract_inverted_index.facilitates | 72 |
| abstract_inverted_index.investigate | 58 |
| abstract_inverted_index.performance | 178 |
| abstract_inverted_index.recognition | 174 |
| abstract_inverted_index.architecture | 102 |
| abstract_inverted_index.complexities | 27 |
| abstract_inverted_index.considerably | 187 |
| abstract_inverted_index.demonstrates | 121 |
| abstract_inverted_index.generalizing | 132 |
| abstract_inverted_index.transformers | 1, 35, 71 |
| abstract_inverted_index.Additionally, | 158 |
| abstract_inverted_index.Transformers. | 118 |
| abstract_inverted_index.applicability | 163 |
| abstract_inverted_index.computational | 129, 189 |
| abstract_inverted_index.observations, | 97 |
| abstract_inverted_index.generalization | 24, 79, 154 |
| abstract_inverted_index.transformer-based | 101 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 11 |
| citation_normalized_percentile |