Enhancing Large Vision Language Models with Self-Training on Image Comprehension Article Swipe
Yihe Deng
,
Pan Lu
,
Fan Yin
,
Ziniu Hu
,
Sheng Shen
,
James Zou
,
Kai‐Wei Chang
,
Wei Wang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.19716
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2405.19716
Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual perception and reasoning capability of LVLMs. To address this, we introduce Self-Training on Image Comprehension (STIC), which emphasizes a self-training approach specifically for image comprehension. First, the model self-constructs a preference dataset for image descriptions using unlabeled images. Preferred responses are generated through a step-by-step prompt, while dis-preferred responses are generated from either corrupted images or misleading prompts. To further self-improve reasoning on the extracted visual information, we let the model reuse a small portion of existing instruction-tuning data and append its self-generated image descriptions to the prompts. We validate the effectiveness of STIC across seven different benchmarks, demonstrating substantial performance gains of 4.0% on average while using 70% less supervised fine-tuning data than the current method. Further studies investigate various components of STIC and highlight its potential to leverage vast quantities of unlabeled images for self-training. Code and data are made publicly available.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2405.19716
- https://arxiv.org/pdf/2405.19716
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399252119
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399252119Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2405.19716Digital Object Identifier
- Title
-
Enhancing Large Vision Language Models with Self-Training on Image ComprehensionWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-05-30Full publication date if available
- Authors
-
Yihe Deng, Pan Lu, Fan Yin, Ziniu Hu, Sheng Shen, James Zou, Kai‐Wei Chang, Wei WangList of authors in order
- Landing page
-
https://arxiv.org/abs/2405.19716Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2405.19716Direct 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/2405.19716Direct OA link when available
- Concepts
-
Comprehension, Training (meteorology), Image (mathematics), Computer science, Artificial intelligence, Computer vision, Natural language processing, Psychology, Cognitive psychology, Geography, Programming language, MeteorologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4399252119 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2405.19716 |
| ids.doi | https://doi.org/10.48550/arxiv.2405.19716 |
| ids.openalex | https://openalex.org/W4399252119 |
| fwci | |
| type | preprint |
| title | Enhancing Large Vision Language Models with Self-Training on Image Comprehension |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11714 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9545000195503235 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1707 |
| topics[0].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[0].display_name | Multimodal Machine Learning Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C511192102 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6694580912590027 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q5156948 |
| concepts[0].display_name | Comprehension |
| concepts[1].id | https://openalex.org/C2777211547 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6065587401390076 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[1].display_name | Training (meteorology) |
| concepts[2].id | https://openalex.org/C115961682 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5868142247200012 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q860623 |
| concepts[2].display_name | Image (mathematics) |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5585402846336365 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.42888548970222473 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C31972630 |
| concepts[5].level | 1 |
| concepts[5].score | 0.3863084614276886 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[5].display_name | Computer vision |
| concepts[6].id | https://openalex.org/C204321447 |
| concepts[6].level | 1 |
| concepts[6].score | 0.36513984203338623 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q30642 |
| concepts[6].display_name | Natural language processing |
| concepts[7].id | https://openalex.org/C15744967 |
| concepts[7].level | 0 |
| concepts[7].score | 0.35456883907318115 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q9418 |
| concepts[7].display_name | Psychology |
| concepts[8].id | https://openalex.org/C180747234 |
| concepts[8].level | 1 |
| concepts[8].score | 0.34942173957824707 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q23373 |
| concepts[8].display_name | Cognitive psychology |
| concepts[9].id | https://openalex.org/C205649164 |
| concepts[9].level | 0 |
| concepts[9].score | 0.09690457582473755 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q1071 |
| concepts[9].display_name | Geography |
| concepts[10].id | https://openalex.org/C199360897 |
| concepts[10].level | 1 |
| concepts[10].score | 0.06923693418502808 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[10].display_name | Programming language |
| concepts[11].id | https://openalex.org/C153294291 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[11].display_name | Meteorology |
| keywords[0].id | https://openalex.org/keywords/comprehension |
| keywords[0].score | 0.6694580912590027 |
| keywords[0].display_name | Comprehension |
| keywords[1].id | https://openalex.org/keywords/training |
| keywords[1].score | 0.6065587401390076 |
| keywords[1].display_name | Training (meteorology) |
| keywords[2].id | https://openalex.org/keywords/image |
| keywords[2].score | 0.5868142247200012 |
| keywords[2].display_name | Image (mathematics) |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5585402846336365 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.42888548970222473 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/computer-vision |
| keywords[5].score | 0.3863084614276886 |
| keywords[5].display_name | Computer vision |
| keywords[6].id | https://openalex.org/keywords/natural-language-processing |
| keywords[6].score | 0.36513984203338623 |
| keywords[6].display_name | Natural language processing |
| keywords[7].id | https://openalex.org/keywords/psychology |
| keywords[7].score | 0.35456883907318115 |
| keywords[7].display_name | Psychology |
| keywords[8].id | https://openalex.org/keywords/cognitive-psychology |
| keywords[8].score | 0.34942173957824707 |
| keywords[8].display_name | Cognitive psychology |
| keywords[9].id | https://openalex.org/keywords/geography |
| keywords[9].score | 0.09690457582473755 |
| keywords[9].display_name | Geography |
| keywords[10].id | https://openalex.org/keywords/programming-language |
| keywords[10].score | 0.06923693418502808 |
| keywords[10].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2405.19716 |
| 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/2405.19716 |
| 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/2405.19716 |
| locations[1].id | doi:10.48550/arxiv.2405.19716 |
| 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.2405.19716 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5109683001 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yihe Deng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Deng, Yihe |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100567599 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-2193-8415 |
| authorships[1].author.display_name | Pan Lu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lu, Pan |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5053347296 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-8028-2217 |
| authorships[2].author.display_name | Fan Yin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yin, Fan |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5114973490 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-4663-0166 |
| authorships[3].author.display_name | Ziniu Hu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hu, Ziniu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100784815 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-8773-6365 |
| authorships[4].author.display_name | Sheng Shen |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Shen, Sheng |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5005779176 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-8880-4764 |
| authorships[5].author.display_name | James Zou |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Zou, James |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5073201681 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-4991-5274 |
| authorships[6].author.display_name | Kai‐Wei Chang |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Chang, Kai-Wei |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5100335759 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-3733-3939 |
| authorships[7].author.display_name | Wei Wang |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Wang, Wei |
| authorships[7].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/2405.19716 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2024-06-01T00:00:00 |
| display_name | Enhancing Large Vision Language Models with Self-Training on Image Comprehension |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11714 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9545000195503235 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1707 |
| primary_topic.subfield.display_name | Computer Vision and Pattern Recognition |
| primary_topic.display_name | Multimodal Machine Learning Applications |
| related_works | https://openalex.org/W230091440, https://openalex.org/W2233261550, https://openalex.org/W2810751659, https://openalex.org/W258997015, https://openalex.org/W2997094352, https://openalex.org/W3216976533, https://openalex.org/W100620283, https://openalex.org/W2495260952, https://openalex.org/W4366179611, https://openalex.org/W2996078371 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2405.19716 |
| 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/2405.19716 |
| 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/2405.19716 |
| primary_location.id | pmh:oai:arXiv.org:2405.19716 |
| 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/2405.19716 |
| 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/2405.19716 |
| publication_date | 2024-05-30 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 71, 95, 106, 120, 149 |
| abstract_inverted_index.To | 83, 135 |
| abstract_inverted_index.We | 165 |
| abstract_inverted_index.by | 62 |
| abstract_inverted_index.in | 52 |
| abstract_inverted_index.is | 41 |
| abstract_inverted_index.of | 19, 81, 152, 169, 179, 199, 209 |
| abstract_inverted_index.on | 89, 139, 181 |
| abstract_inverted_index.or | 132 |
| abstract_inverted_index.to | 22, 45, 55, 162, 205 |
| abstract_inverted_index.we | 86, 144 |
| abstract_inverted_index.70% | 185 |
| abstract_inverted_index.and | 29, 43, 78, 156, 201, 215 |
| abstract_inverted_index.are | 117, 126, 217 |
| abstract_inverted_index.for | 26, 59, 99, 109, 212 |
| abstract_inverted_index.its | 158, 203 |
| abstract_inverted_index.let | 145 |
| abstract_inverted_index.own | 65 |
| abstract_inverted_index.the | 16, 20, 57, 74, 103, 140, 146, 163, 167, 191 |
| abstract_inverted_index.4.0% | 180 |
| abstract_inverted_index.Code | 214 |
| abstract_inverted_index.STIC | 170, 200 |
| abstract_inverted_index.been | 50 |
| abstract_inverted_index.data | 61, 155, 189, 216 |
| abstract_inverted_index.from | 128 |
| abstract_inverted_index.have | 49 |
| abstract_inverted_index.less | 186 |
| abstract_inverted_index.made | 218 |
| abstract_inverted_index.need | 58 |
| abstract_inverted_index.than | 190 |
| abstract_inverted_index.this | 34 |
| abstract_inverted_index.vast | 207 |
| abstract_inverted_index.with | 10 |
| abstract_inverted_index.Image | 90 |
| abstract_inverted_index.Large | 0 |
| abstract_inverted_index.data, | 39 |
| abstract_inverted_index.gains | 178 |
| abstract_inverted_index.image | 24, 100, 110, 160 |
| abstract_inverted_index.large | 6 |
| abstract_inverted_index.model | 21, 104, 147 |
| abstract_inverted_index.reuse | 148 |
| abstract_inverted_index.seven | 172 |
| abstract_inverted_index.small | 150 |
| abstract_inverted_index.this, | 85 |
| abstract_inverted_index.using | 112, 184 |
| abstract_inverted_index.which | 40, 93 |
| abstract_inverted_index.while | 123, 183 |
| abstract_inverted_index.(LLMs) | 9 |
| abstract_inverted_index.First, | 102 |
| abstract_inverted_index.LVLMs. | 82 |
| abstract_inverted_index.across | 171 |
| abstract_inverted_index.append | 157 |
| abstract_inverted_index.costly | 42 |
| abstract_inverted_index.either | 129 |
| abstract_inverted_index.images | 131, 211 |
| abstract_inverted_index.inputs | 25 |
| abstract_inverted_index.models | 3, 8 |
| abstract_inverted_index.unique | 75 |
| abstract_inverted_index.vision | 1, 12 |
| abstract_inverted_index.visual | 76, 142 |
| abstract_inverted_index.(LVLMs) | 4 |
| abstract_inverted_index.(STIC), | 92 |
| abstract_inverted_index.Further | 194 |
| abstract_inverted_index.address | 84 |
| abstract_inverted_index.average | 182 |
| abstract_inverted_index.conduct | 30 |
| abstract_inverted_index.current | 192 |
| abstract_inverted_index.dataset | 108 |
| abstract_inverted_index.further | 136 |
| abstract_inverted_index.images. | 114 |
| abstract_inverted_index.labeled | 60 |
| abstract_inverted_index.method. | 193 |
| abstract_inverted_index.model's | 64 |
| abstract_inverted_index.portion | 151 |
| abstract_inverted_index.prompt, | 122 |
| abstract_inverted_index.queries | 28 |
| abstract_inverted_index.remains | 70 |
| abstract_inverted_index.studies | 195 |
| abstract_inverted_index.thereby | 14 |
| abstract_inverted_index.through | 119 |
| abstract_inverted_index.various | 197 |
| abstract_inverted_index.However, | 67 |
| abstract_inverted_index.acquire. | 46 |
| abstract_inverted_index.approach | 97 |
| abstract_inverted_index.existing | 153 |
| abstract_inverted_index.language | 2, 7 |
| abstract_inverted_index.leverage | 206 |
| abstract_inverted_index.prompts. | 134, 164 |
| abstract_inverted_index.publicly | 219 |
| abstract_inverted_index.requires | 36 |
| abstract_inverted_index.settings | 54 |
| abstract_inverted_index.validate | 166 |
| abstract_inverted_index.Improving | 33 |
| abstract_inverted_index.Preferred | 115 |
| abstract_inverted_index.alleviate | 56 |
| abstract_inverted_index.challenge | 72 |
| abstract_inverted_index.corrupted | 130 |
| abstract_inverted_index.different | 27, 173 |
| abstract_inverted_index.effective | 51, 68 |
| abstract_inverted_index.encoders, | 13 |
| abstract_inverted_index.extracted | 141 |
| abstract_inverted_index.generated | 118, 127 |
| abstract_inverted_index.highlight | 202 |
| abstract_inverted_index.integrate | 5 |
| abstract_inverted_index.introduce | 87 |
| abstract_inverted_index.potential | 204 |
| abstract_inverted_index.reasoning | 79, 138 |
| abstract_inverted_index.regarding | 73 |
| abstract_inverted_index.responses | 116, 125 |
| abstract_inverted_index.unlabeled | 113, 210 |
| abstract_inverted_index.activating | 15 |
| abstract_inverted_index.approaches | 48 |
| abstract_inverted_index.available. | 220 |
| abstract_inverted_index.capability | 18, 35, 80 |
| abstract_inverted_index.components | 198 |
| abstract_inverted_index.emphasizes | 94 |
| abstract_inverted_index.leveraging | 63 |
| abstract_inverted_index.misleading | 133 |
| abstract_inverted_index.perception | 17, 77 |
| abstract_inverted_index.preference | 107 |
| abstract_inverted_index.quantities | 208 |
| abstract_inverted_index.reasoning. | 32 |
| abstract_inverted_index.subsequent | 31 |
| abstract_inverted_index.supervised | 187 |
| abstract_inverted_index.understand | 23 |
| abstract_inverted_index.benchmarks, | 174 |
| abstract_inverted_index.fine-tuning | 188 |
| abstract_inverted_index.generation. | 66 |
| abstract_inverted_index.investigate | 196 |
| abstract_inverted_index.performance | 177 |
| abstract_inverted_index.pre-trained | 11 |
| abstract_inverted_index.substantial | 176 |
| abstract_inverted_index.descriptions | 111, 161 |
| abstract_inverted_index.high-quality | 37 |
| abstract_inverted_index.information, | 143 |
| abstract_inverted_index.self-improve | 137 |
| abstract_inverted_index.single-modal | 53 |
| abstract_inverted_index.specifically | 98 |
| abstract_inverted_index.step-by-step | 121 |
| abstract_inverted_index.Comprehension | 91 |
| abstract_inverted_index.Self-Training | 88 |
| abstract_inverted_index.Self-training | 47 |
| abstract_inverted_index.demonstrating | 175 |
| abstract_inverted_index.dis-preferred | 124 |
| abstract_inverted_index.effectiveness | 168 |
| abstract_inverted_index.self-training | 69, 96 |
| abstract_inverted_index.comprehension. | 101 |
| abstract_inverted_index.self-generated | 159 |
| abstract_inverted_index.self-training. | 213 |
| abstract_inverted_index.labor-intensive | 44 |
| abstract_inverted_index.self-constructs | 105 |
| abstract_inverted_index.vision-language | 38 |
| abstract_inverted_index.instruction-tuning | 154 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |