RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation Article Swipe
Chao Yu
,
Yuanqing Wang
,
Zhen Guo
,
Hao Lin
,
Si Xu
,
Huaiyu Zang
,
Quanlu Zhang
,
Yongji Wu
,
Chunyang Zhu
,
Junhao Hu
,
Zixiao Huang
,
Mingjie Wei
,
Yuqing Xie
,
Ke Yang
,
Bo Dai
,
Zeshui Xu
,
Xiangyuan Wang
,
Xu Fu
,
Zhihao Liu
,
Kang Chen
,
Weilin Liu
,
Gang Liu
,
Boxun Li
,
Jianlei Yang
,
Z. W. Yang
,
Guohao Dai
,
Yu Wang
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.15965
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2509.15965
Reinforcement learning (RL) has demonstrated immense potential in advancing artificial general intelligence, agentic intelligence, and embodied intelligence. However, the inherent heterogeneity and dynamicity of RL workflows often lead to low hardware utilization and slow training on existing systems. In this paper, we present RLinf, a high-performance RL training system based on our key observation that the major roadblock to efficient RL training lies in system flexibility. To maximize flexibility and efficiency, RLinf is built atop a novel RL system design paradigm called macro-to-micro flow transformation (M2Flow), which automatically breaks down high-level, easy-to-compose RL workflows at both the temporal and spatial dimensions, and recomposes them into optimized execution flows. Supported by RLinf worker's adaptive communication capability, we devise context switching and elastic pipelining to realize M2Flow transformation, and a profiling-guided scheduling policy to generate optimal execution plans. Extensive evaluations on both reasoning RL and embodied RL tasks demonstrate that RLinf consistently outperforms state-of-the-art systems, achieving 1.1x-2.13x speedup in end-to-end training throughput.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2509.15965
- https://arxiv.org/pdf/2509.15965
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4414742490
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4414742490Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2509.15965Digital Object Identifier
- Title
-
RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow TransformationWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-09-19Full publication date if available
- Authors
-
Chao Yu, Yuanqing Wang, Zhen Guo, Hao Lin, Si Xu, Huaiyu Zang, Quanlu Zhang, Yongji Wu, Chunyang Zhu, Junhao Hu, Zixiao Huang, Mingjie Wei, Yuqing Xie, Ke Yang, Bo Dai, Zeshui Xu, Xiangyuan Wang, Xu Fu, Zhihao Liu, Kang Chen, Weilin Liu, Gang Liu, Boxun Li, Jianlei Yang, Z. W. Yang, Guohao Dai, Yu WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2509.15965Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2509.15965Direct 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/2509.15965Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4414742490 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2509.15965 |
| ids.doi | https://doi.org/10.48550/arxiv.2509.15965 |
| ids.openalex | https://openalex.org/W4414742490 |
| fwci | |
| type | preprint |
| title | RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10462 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8895000219345093 |
| 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 | Reinforcement Learning in Robotics |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2509.15965 |
| 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/2509.15965 |
| 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/2509.15965 |
| locations[1].id | doi:10.48550/arxiv.2509.15965 |
| 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.2509.15965 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100622626 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1517-2564 |
| authorships[0].author.display_name | Chao Yu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yu, Chao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100321635 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9441-9395 |
| authorships[1].author.display_name | Yuanqing Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Yuanqing |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100329567 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-8615-3830 |
| authorships[2].author.display_name | Zhen Guo |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Guo, Zhen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5013129858 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-0828-6763 |
| authorships[3].author.display_name | Hao Lin |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lin, Hao |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5101179925 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Si Xu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Xu, Si |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5008034459 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-8550-3827 |
| authorships[5].author.display_name | Huaiyu Zang |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zang, Hongzhi |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5085281913 |
| authorships[6].author.orcid | https://orcid.org/0000-0003-0557-1104 |
| authorships[6].author.display_name | Quanlu Zhang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Zhang, Quanlu |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5102960230 |
| authorships[7].author.orcid | https://orcid.org/0009-0006-4329-6296 |
| authorships[7].author.display_name | Yongji Wu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Wu, Yongji |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5021426486 |
| authorships[8].author.orcid | |
| authorships[8].author.display_name | Chunyang Zhu |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Zhu, Chunyang |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5100511212 |
| authorships[9].author.orcid | |
| authorships[9].author.display_name | Junhao Hu |
| authorships[9].author_position | middle |
| authorships[9].raw_author_name | Hu, Junhao |
| authorships[9].is_corresponding | False |
| authorships[10].author.id | https://openalex.org/A5051561378 |
| authorships[10].author.orcid | |
| authorships[10].author.display_name | Zixiao Huang |
| authorships[10].author_position | middle |
| authorships[10].raw_author_name | Huang, Zixiao |
| authorships[10].is_corresponding | False |
| authorships[11].author.id | https://openalex.org/A5044503694 |
| authorships[11].author.orcid | https://orcid.org/0000-0001-7601-4749 |
| authorships[11].author.display_name | Mingjie Wei |
| authorships[11].author_position | middle |
| authorships[11].raw_author_name | Wei, Mingjie |
| authorships[11].is_corresponding | False |
| authorships[12].author.id | https://openalex.org/A5027116236 |
| authorships[12].author.orcid | https://orcid.org/0000-0003-3996-2234 |
| authorships[12].author.display_name | Yuqing Xie |
| authorships[12].author_position | middle |
| authorships[12].raw_author_name | Xie, Yuqing |
| authorships[12].is_corresponding | False |
| authorships[13].author.id | https://openalex.org/A5101547265 |
| authorships[13].author.orcid | https://orcid.org/0009-0008-0061-3268 |
| authorships[13].author.display_name | Ke Yang |
| authorships[13].author_position | middle |
| authorships[13].raw_author_name | Yang, Ke |
| authorships[13].is_corresponding | False |
| authorships[14].author.id | https://openalex.org/A5101416182 |
| authorships[14].author.orcid | https://orcid.org/0000-0003-1862-7234 |
| authorships[14].author.display_name | Bo Dai |
| authorships[14].author_position | middle |
| authorships[14].raw_author_name | Dai, Bo |
| authorships[14].is_corresponding | False |
| authorships[15].author.id | https://openalex.org/A5100437308 |
| authorships[15].author.orcid | https://orcid.org/0000-0003-3547-2908 |
| authorships[15].author.display_name | Zeshui Xu |
| authorships[15].author_position | middle |
| authorships[15].raw_author_name | Xu, Zhexuan |
| authorships[15].is_corresponding | False |
| authorships[16].author.id | https://openalex.org/A5102754183 |
| authorships[16].author.orcid | https://orcid.org/0000-0002-8428-5757 |
| authorships[16].author.display_name | Xiangyuan Wang |
| authorships[16].author_position | middle |
| authorships[16].raw_author_name | Wang, Xiangyuan |
| authorships[16].is_corresponding | False |
| authorships[17].author.id | https://openalex.org/A5101571491 |
| authorships[17].author.orcid | https://orcid.org/0009-0006-6771-9871 |
| authorships[17].author.display_name | Xu Fu |
| authorships[17].author_position | middle |
| authorships[17].raw_author_name | Fu, Xu |
| authorships[17].is_corresponding | False |
| authorships[18].author.id | https://openalex.org/A5100421209 |
| authorships[18].author.orcid | https://orcid.org/0000-0002-0222-912X |
| authorships[18].author.display_name | Zhihao Liu |
| authorships[18].author_position | middle |
| authorships[18].raw_author_name | Liu, Zhihao |
| authorships[18].is_corresponding | False |
| authorships[19].author.id | https://openalex.org/A5087386668 |
| authorships[19].author.orcid | https://orcid.org/0000-0002-6363-740X |
| authorships[19].author.display_name | Kang Chen |
| authorships[19].author_position | middle |
| authorships[19].raw_author_name | Chen, Kang |
| authorships[19].is_corresponding | False |
| authorships[20].author.id | https://openalex.org/A5100690567 |
| authorships[20].author.orcid | https://orcid.org/0000-0002-7486-6697 |
| authorships[20].author.display_name | Weilin Liu |
| authorships[20].author_position | middle |
| authorships[20].raw_author_name | Liu, Weilin |
| authorships[20].is_corresponding | False |
| authorships[21].author.id | https://openalex.org/A5100412437 |
| authorships[21].author.orcid | https://orcid.org/0000-0002-3444-3649 |
| authorships[21].author.display_name | Gang Liu |
| authorships[21].author_position | middle |
| authorships[21].raw_author_name | Liu, Gang |
| authorships[21].is_corresponding | False |
| authorships[22].author.id | https://openalex.org/A5101982776 |
| authorships[22].author.orcid | https://orcid.org/0000-0002-6370-1723 |
| authorships[22].author.display_name | Boxun Li |
| authorships[22].author_position | middle |
| authorships[22].raw_author_name | Li, Boxun |
| authorships[22].is_corresponding | False |
| authorships[23].author.id | https://openalex.org/A5115580368 |
| authorships[23].author.orcid | https://orcid.org/0000-0003-1920-2385 |
| authorships[23].author.display_name | Jianlei Yang |
| authorships[23].author_position | middle |
| authorships[23].raw_author_name | Yang, Jianlei |
| authorships[23].is_corresponding | False |
| authorships[24].author.id | https://openalex.org/A5020521166 |
| authorships[24].author.orcid | https://orcid.org/0000-0003-4371-1032 |
| authorships[24].author.display_name | Z. W. Yang |
| authorships[24].author_position | middle |
| authorships[24].raw_author_name | Yang, Zhi |
| authorships[24].is_corresponding | False |
| authorships[25].author.id | https://openalex.org/A5015946486 |
| authorships[25].author.orcid | https://orcid.org/0000-0003-0849-3252 |
| authorships[25].author.display_name | Guohao Dai |
| authorships[25].author_position | middle |
| authorships[25].raw_author_name | Dai, Guohao |
| authorships[25].is_corresponding | False |
| authorships[26].author.id | https://openalex.org/A5101828422 |
| authorships[26].author.orcid | https://orcid.org/0000-0002-3639-3147 |
| authorships[26].author.display_name | Yu Wang |
| authorships[26].author_position | last |
| authorships[26].raw_author_name | Wang, Yu |
| authorships[26].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/2509.15965 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10462 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8895000219345093 |
| 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 | Reinforcement Learning in Robotics |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2509.15965 |
| 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/2509.15965 |
| 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/2509.15965 |
| primary_location.id | pmh:oai:arXiv.org:2509.15965 |
| 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/2509.15965 |
| 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/2509.15965 |
| publication_date | 2025-09-19 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 44, 75, 127 |
| abstract_inverted_index.In | 38 |
| abstract_inverted_index.RL | 24, 46, 60, 77, 92, 141, 144 |
| abstract_inverted_index.To | 66 |
| abstract_inverted_index.at | 94 |
| abstract_inverted_index.by | 109 |
| abstract_inverted_index.in | 7, 63, 156 |
| abstract_inverted_index.is | 72 |
| abstract_inverted_index.of | 23 |
| abstract_inverted_index.on | 35, 50, 138 |
| abstract_inverted_index.to | 28, 58, 122, 131 |
| abstract_inverted_index.we | 41, 115 |
| abstract_inverted_index.and | 14, 21, 32, 69, 98, 101, 119, 126, 142 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.key | 52 |
| abstract_inverted_index.low | 29 |
| abstract_inverted_index.our | 51 |
| abstract_inverted_index.the | 18, 55, 96 |
| abstract_inverted_index.(RL) | 2 |
| abstract_inverted_index.atop | 74 |
| abstract_inverted_index.both | 95, 139 |
| abstract_inverted_index.down | 89 |
| abstract_inverted_index.flow | 83 |
| abstract_inverted_index.into | 104 |
| abstract_inverted_index.lead | 27 |
| abstract_inverted_index.lies | 62 |
| abstract_inverted_index.slow | 33 |
| abstract_inverted_index.that | 54, 147 |
| abstract_inverted_index.them | 103 |
| abstract_inverted_index.this | 39 |
| abstract_inverted_index.RLinf | 71, 110, 148 |
| abstract_inverted_index.based | 49 |
| abstract_inverted_index.built | 73 |
| abstract_inverted_index.major | 56 |
| abstract_inverted_index.novel | 76 |
| abstract_inverted_index.often | 26 |
| abstract_inverted_index.tasks | 145 |
| abstract_inverted_index.which | 86 |
| abstract_inverted_index.M2Flow | 124 |
| abstract_inverted_index.RLinf, | 43 |
| abstract_inverted_index.breaks | 88 |
| abstract_inverted_index.called | 81 |
| abstract_inverted_index.design | 79 |
| abstract_inverted_index.devise | 116 |
| abstract_inverted_index.flows. | 107 |
| abstract_inverted_index.paper, | 40 |
| abstract_inverted_index.plans. | 135 |
| abstract_inverted_index.policy | 130 |
| abstract_inverted_index.system | 48, 64, 78 |
| abstract_inverted_index.agentic | 12 |
| abstract_inverted_index.context | 117 |
| abstract_inverted_index.elastic | 120 |
| abstract_inverted_index.general | 10 |
| abstract_inverted_index.immense | 5 |
| abstract_inverted_index.optimal | 133 |
| abstract_inverted_index.present | 42 |
| abstract_inverted_index.realize | 123 |
| abstract_inverted_index.spatial | 99 |
| abstract_inverted_index.speedup | 155 |
| abstract_inverted_index.However, | 17 |
| abstract_inverted_index.adaptive | 112 |
| abstract_inverted_index.embodied | 15, 143 |
| abstract_inverted_index.existing | 36 |
| abstract_inverted_index.generate | 132 |
| abstract_inverted_index.hardware | 30 |
| abstract_inverted_index.inherent | 19 |
| abstract_inverted_index.learning | 1 |
| abstract_inverted_index.maximize | 67 |
| abstract_inverted_index.paradigm | 80 |
| abstract_inverted_index.systems, | 152 |
| abstract_inverted_index.systems. | 37 |
| abstract_inverted_index.temporal | 97 |
| abstract_inverted_index.training | 34, 47, 61, 158 |
| abstract_inverted_index.worker's | 111 |
| abstract_inverted_index.(M2Flow), | 85 |
| abstract_inverted_index.Extensive | 136 |
| abstract_inverted_index.Supported | 108 |
| abstract_inverted_index.achieving | 153 |
| abstract_inverted_index.advancing | 8 |
| abstract_inverted_index.efficient | 59 |
| abstract_inverted_index.execution | 106, 134 |
| abstract_inverted_index.optimized | 105 |
| abstract_inverted_index.potential | 6 |
| abstract_inverted_index.reasoning | 140 |
| abstract_inverted_index.roadblock | 57 |
| abstract_inverted_index.switching | 118 |
| abstract_inverted_index.workflows | 25, 93 |
| abstract_inverted_index.1.1x-2.13x | 154 |
| abstract_inverted_index.artificial | 9 |
| abstract_inverted_index.dynamicity | 22 |
| abstract_inverted_index.end-to-end | 157 |
| abstract_inverted_index.pipelining | 121 |
| abstract_inverted_index.recomposes | 102 |
| abstract_inverted_index.scheduling | 129 |
| abstract_inverted_index.capability, | 114 |
| abstract_inverted_index.demonstrate | 146 |
| abstract_inverted_index.dimensions, | 100 |
| abstract_inverted_index.efficiency, | 70 |
| abstract_inverted_index.evaluations | 137 |
| abstract_inverted_index.flexibility | 68 |
| abstract_inverted_index.high-level, | 90 |
| abstract_inverted_index.observation | 53 |
| abstract_inverted_index.outperforms | 150 |
| abstract_inverted_index.throughput. | 159 |
| abstract_inverted_index.utilization | 31 |
| abstract_inverted_index.consistently | 149 |
| abstract_inverted_index.demonstrated | 4 |
| abstract_inverted_index.flexibility. | 65 |
| abstract_inverted_index.Reinforcement | 0 |
| abstract_inverted_index.automatically | 87 |
| abstract_inverted_index.communication | 113 |
| abstract_inverted_index.heterogeneity | 20 |
| abstract_inverted_index.intelligence, | 11, 13 |
| abstract_inverted_index.intelligence. | 16 |
| abstract_inverted_index.macro-to-micro | 82 |
| abstract_inverted_index.transformation | 84 |
| abstract_inverted_index.easy-to-compose | 91 |
| abstract_inverted_index.transformation, | 125 |
| abstract_inverted_index.high-performance | 45 |
| abstract_inverted_index.profiling-guided | 128 |
| abstract_inverted_index.state-of-the-art | 151 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 27 |
| citation_normalized_percentile |