Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.09617
Although Large Language Models (LLMs) have shown promise for human-like conversations, they are primarily pre-trained on text data. Incorporating audio or video improves performance, but collecting large-scale multimodal data and pre-training multimodal LLMs is challenging. To this end, we propose a Fusion Low Rank Adaptation (FLoRA) technique that efficiently adapts a pre-trained unimodal LLM to consume new, previously unseen modalities via low rank adaptation. For device-directed speech detection, using FLoRA, the multimodal LLM achieves 22% relative reduction in equal error rate (EER) over the text-only approach and attains performance parity with its full fine-tuning (FFT) counterpart while needing to tune only a fraction of its parameters. Furthermore, with the newly introduced adapter dropout, FLoRA is robust to missing data, improving over FFT by 20% lower EER and 56% lower false accept rate. The proposed approach scales well for model sizes from 16M to 3B parameters.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2406.09617
- https://arxiv.org/pdf/2406.09617
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399758722
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399758722Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2406.09617Digital Object Identifier
- Title
-
Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech DetectionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-13Full publication date if available
- Authors
-
Shruti Palaskar, Oggi Rudovic, Sameer Dharur, Florian Pesce, Gautam Krishna, Aswin Sivaraman, Jack Berkowitz, Ahmed Hussen Abdelaziz, Saurabh Adya, Ahmed H. TewfikList of authors in order
- Landing page
-
https://arxiv.org/abs/2406.09617Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2406.09617Direct 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/2406.09617Direct OA link when available
- Concepts
-
Rank (graph theory), Adaptation (eye), Computer science, Fusion, Speech recognition, Voice activity detection, Natural language processing, Artificial intelligence, Speech processing, Psychology, Linguistics, Mathematics, Neuroscience, Philosophy, CombinatoricsTop 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/W4399758722 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2406.09617 |
| ids.doi | https://doi.org/10.48550/arxiv.2406.09617 |
| ids.openalex | https://openalex.org/W4399758722 |
| fwci | |
| type | preprint |
| title | Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10201 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9865999817848206 |
| 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 | Speech Recognition and Synthesis |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C164226766 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6184766888618469 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7293202 |
| concepts[0].display_name | Rank (graph theory) |
| concepts[1].id | https://openalex.org/C139807058 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6112086176872253 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q352374 |
| concepts[1].display_name | Adaptation (eye) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6107502579689026 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C158525013 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5607901811599731 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q2593739 |
| concepts[3].display_name | Fusion |
| concepts[4].id | https://openalex.org/C28490314 |
| concepts[4].level | 1 |
| concepts[4].score | 0.5570576190948486 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q189436 |
| concepts[4].display_name | Speech recognition |
| concepts[5].id | https://openalex.org/C204201278 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4331420660018921 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q1332614 |
| concepts[5].display_name | Voice activity detection |
| concepts[6].id | https://openalex.org/C204321447 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3722025454044342 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[6].display_name | Natural language processing |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.3658641576766968 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C61328038 |
| concepts[8].level | 2 |
| concepts[8].score | 0.222753643989563 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q3358061 |
| concepts[8].display_name | Speech processing |
| concepts[9].id | https://openalex.org/C15744967 |
| concepts[9].level | 0 |
| concepts[9].score | 0.2197432518005371 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[9].display_name | Psychology |
| concepts[10].id | https://openalex.org/C41895202 |
| concepts[10].level | 1 |
| concepts[10].score | 0.18191388249397278 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[10].display_name | Linguistics |
| concepts[11].id | https://openalex.org/C33923547 |
| concepts[11].level | 0 |
| concepts[11].score | 0.10991591215133667 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[11].display_name | Mathematics |
| concepts[12].id | https://openalex.org/C169760540 |
| concepts[12].level | 1 |
| concepts[12].score | 0.05714622139930725 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q207011 |
| concepts[12].display_name | Neuroscience |
| concepts[13].id | https://openalex.org/C138885662 |
| concepts[13].level | 0 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[13].display_name | Philosophy |
| concepts[14].id | https://openalex.org/C114614502 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q76592 |
| concepts[14].display_name | Combinatorics |
| keywords[0].id | https://openalex.org/keywords/rank |
| keywords[0].score | 0.6184766888618469 |
| keywords[0].display_name | Rank (graph theory) |
| keywords[1].id | https://openalex.org/keywords/adaptation |
| keywords[1].score | 0.6112086176872253 |
| keywords[1].display_name | Adaptation (eye) |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.6107502579689026 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/fusion |
| keywords[3].score | 0.5607901811599731 |
| keywords[3].display_name | Fusion |
| keywords[4].id | https://openalex.org/keywords/speech-recognition |
| keywords[4].score | 0.5570576190948486 |
| keywords[4].display_name | Speech recognition |
| keywords[5].id | https://openalex.org/keywords/voice-activity-detection |
| keywords[5].score | 0.4331420660018921 |
| keywords[5].display_name | Voice activity detection |
| keywords[6].id | https://openalex.org/keywords/natural-language-processing |
| keywords[6].score | 0.3722025454044342 |
| keywords[6].display_name | Natural language processing |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.3658641576766968 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/speech-processing |
| keywords[8].score | 0.222753643989563 |
| keywords[8].display_name | Speech processing |
| keywords[9].id | https://openalex.org/keywords/psychology |
| keywords[9].score | 0.2197432518005371 |
| keywords[9].display_name | Psychology |
| keywords[10].id | https://openalex.org/keywords/linguistics |
| keywords[10].score | 0.18191388249397278 |
| keywords[10].display_name | Linguistics |
| keywords[11].id | https://openalex.org/keywords/mathematics |
| keywords[11].score | 0.10991591215133667 |
| keywords[11].display_name | Mathematics |
| keywords[12].id | https://openalex.org/keywords/neuroscience |
| keywords[12].score | 0.05714622139930725 |
| keywords[12].display_name | Neuroscience |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2406.09617 |
| 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/2406.09617 |
| 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/2406.09617 |
| locations[1].id | doi:10.48550/arxiv.2406.09617 |
| 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.2406.09617 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5036933477 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8637-1897 |
| authorships[0].author.display_name | Shruti Palaskar |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Palaskar, Shruti |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5076868683 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Oggi Rudovic |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Rudovic, Oggi |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5046750126 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-7131-4539 |
| authorships[2].author.display_name | Sameer Dharur |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Dharur, Sameer |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5083037438 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Florian Pesce |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Pesce, Florian |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5114026387 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Gautam Krishna |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Krishna, Gautam |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5085011950 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2248-4846 |
| authorships[5].author.display_name | Aswin Sivaraman |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Sivaraman, Aswin |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5090461939 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Jack Berkowitz |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Berkowitz, Jack |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5101807751 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-8027-4666 |
| authorships[7].author.display_name | Ahmed Hussen Abdelaziz |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Abdelaziz, Ahmed Hussen |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5068392026 |
| authorships[8].author.orcid | https://orcid.org/0009-0000-4533-6577 |
| authorships[8].author.display_name | Saurabh Adya |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Adya, Saurabh |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5089360428 |
| authorships[9].author.orcid | https://orcid.org/0000-0002-2384-4391 |
| authorships[9].author.display_name | Ahmed H. Tewfik |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Tewfik, Ahmed |
| authorships[9].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2406.09617 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Multimodal Large Language Models with Fusion Low Rank Adaptation for Device Directed Speech Detection |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10201 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9865999817848206 |
| 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 | Speech Recognition and Synthesis |
| related_works | https://openalex.org/W3135230428, https://openalex.org/W2904739811, https://openalex.org/W2152158029, https://openalex.org/W2012540220, https://openalex.org/W2131711534, https://openalex.org/W2559837139, https://openalex.org/W1151175420, https://openalex.org/W2166690696, https://openalex.org/W2407342067, https://openalex.org/W2541680182 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2406.09617 |
| 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/2406.09617 |
| 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/2406.09617 |
| primary_location.id | pmh:oai:arXiv.org:2406.09617 |
| 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/2406.09617 |
| 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/2406.09617 |
| publication_date | 2024-06-13 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 40, 50, 101 |
| abstract_inverted_index.3B | 143 |
| abstract_inverted_index.To | 35 |
| abstract_inverted_index.by | 122 |
| abstract_inverted_index.in | 77 |
| abstract_inverted_index.is | 33, 114 |
| abstract_inverted_index.of | 103 |
| abstract_inverted_index.on | 15 |
| abstract_inverted_index.or | 20 |
| abstract_inverted_index.to | 54, 98, 116, 142 |
| abstract_inverted_index.we | 38 |
| abstract_inverted_index.16M | 141 |
| abstract_inverted_index.20% | 123 |
| abstract_inverted_index.22% | 74 |
| abstract_inverted_index.56% | 127 |
| abstract_inverted_index.EER | 125 |
| abstract_inverted_index.FFT | 121 |
| abstract_inverted_index.For | 64 |
| abstract_inverted_index.LLM | 53, 72 |
| abstract_inverted_index.Low | 42 |
| abstract_inverted_index.The | 132 |
| abstract_inverted_index.and | 29, 86, 126 |
| abstract_inverted_index.are | 12 |
| abstract_inverted_index.but | 24 |
| abstract_inverted_index.for | 8, 137 |
| abstract_inverted_index.its | 91, 104 |
| abstract_inverted_index.low | 61 |
| abstract_inverted_index.the | 70, 83, 108 |
| abstract_inverted_index.via | 60 |
| abstract_inverted_index.LLMs | 32 |
| abstract_inverted_index.Rank | 43 |
| abstract_inverted_index.data | 28 |
| abstract_inverted_index.end, | 37 |
| abstract_inverted_index.from | 140 |
| abstract_inverted_index.full | 92 |
| abstract_inverted_index.have | 5 |
| abstract_inverted_index.new, | 56 |
| abstract_inverted_index.only | 100 |
| abstract_inverted_index.over | 82, 120 |
| abstract_inverted_index.rank | 62 |
| abstract_inverted_index.rate | 80 |
| abstract_inverted_index.text | 16 |
| abstract_inverted_index.that | 47 |
| abstract_inverted_index.they | 11 |
| abstract_inverted_index.this | 36 |
| abstract_inverted_index.tune | 99 |
| abstract_inverted_index.well | 136 |
| abstract_inverted_index.with | 90, 107 |
| abstract_inverted_index.(EER) | 81 |
| abstract_inverted_index.(FFT) | 94 |
| abstract_inverted_index.FLoRA | 113 |
| abstract_inverted_index.Large | 1 |
| abstract_inverted_index.audio | 19 |
| abstract_inverted_index.data, | 118 |
| abstract_inverted_index.data. | 17 |
| abstract_inverted_index.equal | 78 |
| abstract_inverted_index.error | 79 |
| abstract_inverted_index.false | 129 |
| abstract_inverted_index.lower | 124, 128 |
| abstract_inverted_index.model | 138 |
| abstract_inverted_index.newly | 109 |
| abstract_inverted_index.rate. | 131 |
| abstract_inverted_index.shown | 6 |
| abstract_inverted_index.sizes | 139 |
| abstract_inverted_index.using | 68 |
| abstract_inverted_index.video | 21 |
| abstract_inverted_index.while | 96 |
| abstract_inverted_index.(LLMs) | 4 |
| abstract_inverted_index.FLoRA, | 69 |
| abstract_inverted_index.Fusion | 41 |
| abstract_inverted_index.Models | 3 |
| abstract_inverted_index.accept | 130 |
| abstract_inverted_index.adapts | 49 |
| abstract_inverted_index.parity | 89 |
| abstract_inverted_index.robust | 115 |
| abstract_inverted_index.scales | 135 |
| abstract_inverted_index.speech | 66 |
| abstract_inverted_index.unseen | 58 |
| abstract_inverted_index.(FLoRA) | 45 |
| abstract_inverted_index.adapter | 111 |
| abstract_inverted_index.attains | 87 |
| abstract_inverted_index.consume | 55 |
| abstract_inverted_index.missing | 117 |
| abstract_inverted_index.needing | 97 |
| abstract_inverted_index.promise | 7 |
| abstract_inverted_index.propose | 39 |
| abstract_inverted_index.Although | 0 |
| abstract_inverted_index.Language | 2 |
| abstract_inverted_index.achieves | 73 |
| abstract_inverted_index.approach | 85, 134 |
| abstract_inverted_index.dropout, | 112 |
| abstract_inverted_index.fraction | 102 |
| abstract_inverted_index.improves | 22 |
| abstract_inverted_index.proposed | 133 |
| abstract_inverted_index.relative | 75 |
| abstract_inverted_index.unimodal | 52 |
| abstract_inverted_index.improving | 119 |
| abstract_inverted_index.primarily | 13 |
| abstract_inverted_index.reduction | 76 |
| abstract_inverted_index.technique | 46 |
| abstract_inverted_index.text-only | 84 |
| abstract_inverted_index.Adaptation | 44 |
| abstract_inverted_index.collecting | 25 |
| abstract_inverted_index.detection, | 67 |
| abstract_inverted_index.human-like | 9 |
| abstract_inverted_index.introduced | 110 |
| abstract_inverted_index.modalities | 59 |
| abstract_inverted_index.multimodal | 27, 31, 71 |
| abstract_inverted_index.previously | 57 |
| abstract_inverted_index.adaptation. | 63 |
| abstract_inverted_index.counterpart | 95 |
| abstract_inverted_index.efficiently | 48 |
| abstract_inverted_index.fine-tuning | 93 |
| abstract_inverted_index.large-scale | 26 |
| abstract_inverted_index.parameters. | 105, 144 |
| abstract_inverted_index.performance | 88 |
| abstract_inverted_index.pre-trained | 14, 51 |
| abstract_inverted_index.Furthermore, | 106 |
| abstract_inverted_index.challenging. | 34 |
| abstract_inverted_index.performance, | 23 |
| abstract_inverted_index.pre-training | 30 |
| abstract_inverted_index.Incorporating | 18 |
| abstract_inverted_index.conversations, | 10 |
| abstract_inverted_index.device-directed | 65 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile |