Spaces:
Running
Running
added citations
Browse files- app/src/content/article.mdx +188 -187
app/src/content/article.mdx
CHANGED
|
@@ -52,193 +52,194 @@ We manually collect **over 180** image-text datasets from the recent literature
|
|
| 52 |
|
| 53 |
<Wide>
|
| 54 |
<Accordion title="FineVision Subsets">
|
| 55 |
-
|Subset Name |Total Images|Total Samples|Total Turns|Total Question Tokens|Total Answer Tokens|Category |
|
| 56 |
-
|
| 57 |
-
|coco_colors |118,287 |118,287 |118,287 |1,301,157 |6,376,672 |Captioning & Knowledge|
|
| 58 |
-
|densefusion_1m |1,058,751 |1,058,751 |1,058,751 |10,692,478 |263,718,217 |Captioning & Knowledge|
|
| 59 |
-
|face_emotion |797 |797 |797 |8,767 |8,066 |Captioning & Knowledge|
|
| 60 |
-
|
|
| 61 |
-
|image_textualization(filtered) |99,573 |99,573 |99,573 |917,577 |19,374,090 |Captioning & Knowledge|
|
| 62 |
-
|laion_gpt4v |9,301 |9,301 |9,301 |93,950 |1,875,283 |Captioning & Knowledge|
|
| 63 |
-
|localized_narratives |199,998 |199,998 |199,998 |2,167,179 |8,021,473 |Captioning & Knowledge|
|
| 64 |
-
|sharegpt4o |57,284 |57,284 |57,284 |558,647 |36,555,323 |Captioning & Knowledge|
|
| 65 |
-
|sharegpt4v(coco) |50,017 |50,017 |50,017 |460,893 |9,825,387 |Captioning & Knowledge|
|
| 66 |
-
|sharegpt4v(knowledge) |1,988 |1,988 |1,988 |18,250 |293,850 |Captioning & Knowledge|
|
| 67 |
-
|sharegpt4v(llava) |29,986 |29,986 |29,986 |275,783 |6,175,899 |Captioning & Knowledge|
|
| 68 |
-
|sharegpt4v(sam) |8,990 |8,990 |8,990 |82,874 |1,668,797 |Captioning & Knowledge|
|
| 69 |
-
|textcaps |21,906 |21,906 |21,906 |240,966 |355,991 |Captioning & Knowledge|
|
| 70 |
-
|chart2text |26,961 |26,961 |30,215 |342,215 |2,670,580 |Chart & Table |
|
| 71 |
-
|chartqa |18,265 |18,265 |28,287 |625,569 |134,793 |Chart & Table |
|
| 72 |
-
|CoSyn_400k_chart |116,814 |116,814 |1,085,882 |17,617,591 |57,641,030 |Chart & Table |
|
| 73 |
-
|CoSyn_400k_table |46,518 |46,518 |416,519 |6,280,455 |23,335,054 |Chart & Table |
|
| 74 |
-
|dvqa |200,000 |200,000 |2,325,316 |44,603,372 |5,477,966 |Chart & Table |
|
| 75 |
-
|figureqa |100,000 |100,000 |1,327,368 |18,515,153 |2,654,736 |Chart & Table |
|
| 76 |
-
|figureqa(mathv360k) |17,587 |17,587 |17,587 |722,959 |97,404 |Chart & Table |
|
| 77 |
-
|finqa |5,276 |5,276 |6,251 |5,552,943 |224,015 |Chart & Table |
|
| 78 |
-
|hitab |2,500 |2,500 |7,782 |177,999 |335,013 |Chart & Table |
|
| 79 |
-
|lrv_chart |1,776 |1,776 |5,372 |76,477 |158,711 |Chart & Table |
|
| 80 |
-
|mmc_instruct |168,178 |168,178 |168,178 |50,008,824 |74,581,055 |Chart & Table |
|
| 81 |
-
|multihiertt |30,875 |7,619 |7,830 |218,840 |244,744 |Chart & Table |
|
| 82 |
-
|plotqa |157,070 |157,070 |20,249,479 |738,371,054 |118,122,387 |Chart & Table |
|
| 83 |
-
|robut_sqa |8,514 |8,514 |34,141 |368,957 |1,794,570 |Chart & Table |
|
| 84 |
-
|robut_wikisql |74,989 |74,989 |86,202 |1,454,920 |9,276,100 |Chart & Table |
|
| 85 |
-
|robut_wtq |38,246 |38,246 |44,096 |587,040 |6,415,830 |Chart & Table |
|
| 86 |
-
|SynthChartNet |500,000 |500,000 |500,000 |2,169,240 |67,392,223 |Chart & Table |
|
| 87 |
-
|tabmwp |22,722 |22,722 |23,021 |639,639 |1,883,243 |Chart & Table |
|
| 88 |
-
|tabmwp(mathv360k) |22,452 |22,452 |22,452 |963,498 |158,042 |Chart & Table |
|
| 89 |
-
|tat_dqa |2,448 |2,207 |13,251 |320,356 |1,177,852 |Chart & Table |
|
| 90 |
-
|tat_qa |2,199 |2,199 |13,215 |989,419 |254,790 |Chart & Table |
|
| 91 |
-
|Unichart |611,925 |611,925 |6,898,324 |96,702,288 |211,989,247 |Chart & Table |
|
| 92 |
-
|vistext |9,969 |9,969 |9,969 |88,770 |1,191,127 |Chart & Table |
|
| 93 |
-
|vqaonbd |39,986 |39,986 |1,254,165 |36,066,807 |5,620,523 |Chart & Table |
|
| 94 |
-
|alfworldgpt |45,073 |45,073 |45,073 |17,864,033 |6,276,573 |General VQA |
|
| 95 |
-
|allava_laion |468,664 |468,664 |937,328 |18,654,303 |145,799,426 |General VQA |
|
| 96 |
-
|allava_vflan |177,078 |177,078 |387,872 |12,444,711 |55,305,642 |General VQA |
|
| 97 |
-
|cambrian(filtered)_processed |83,123 |83,124 |98,534 |1,410,321 |5,503,211 |General VQA |
|
| 98 |
-
|chinesememe |54,212 |54,212 |54,212 |538,938 |21,122,723 |General VQA |
|
| 99 |
-
|cocoqa |46,287 |46,287 |78,736 |1,136,238 |212,480 |General VQA |
|
| 100 |
-
|CoSyn_400k_graphic |26,968 |26,968 |26,968 |1,678,862 |8,235,679 |General VQA |
|
| 101 |
-
|datik |220,537 |222,385 |222,385 |2,234,054 |187,757,952 |General VQA |
|
| 102 |
-
|datikz |47,441 |47,974 |48,296 |441,040 |59,116,193 |General VQA |
|
| 103 |
-
|drivelm |90,049 |4,072 |161,030 |2,399,362 |1,431,417 |General VQA |
|
| 104 |
-
|hateful_memes |8,500 |8,500 |8,500 |128,375 |17,000 |General VQA |
|
| 105 |
-
|iconqa |27,307 |27,307 |29,841 |906,877 |72,492 |General VQA |
|
| 106 |
-
|iconqa(mathv360k) |22,589 |22,589 |22,589 |952,183 |134,029 |General VQA |
|
| 107 |
-
|idk |11,123 |11,123 |27,614 |235,262 |665,247 |General VQA |
|
| 108 |
-
|indoor_qa |3,350 |3,350 |3,350 |36,832 |19,700 |General VQA |
|
| 109 |
-
|LLaVA_Instruct_150K |157,710 |157,710 |361,405 |4,412,600 |28,719,278 |General VQA |
|
| 110 |
-
|llavar_gpt4_20k |19,790 |19,790 |43,167 |546,703 |1,516,730 |General VQA |
|
| 111 |
-
|lnqa |302,780 |302,780 |1,520,942 |16,530,323 |19,027,663 |General VQA |
|
| 112 |
-
|lrv_normal(filtered) |10,489 |10,489 |155,269 |2,108,321 |3,134,247 |General VQA |
|
| 113 |
-
|lvis_instruct4v |222,711 |222,711 |1,050,622 |12,556,173 |43,726,782 |General VQA |
|
| 114 |
-
|mimic_cgd |141,878 |70,939 |141,869 |1,789,740 |4,304,380 |General VQA |
|
| 115 |
-
|
|
| 116 |
-
|mmra |2,048 |1,024 |1,024 |72,523 |25,764 |General VQA |
|
| 117 |
-
|nlvr2 |100,852 |50,426 |86,373 |4,629,641 |172,746 |General VQA |
|
| 118 |
-
|sketchyvqa |8,000 |8,000 |8,000 |182,192 |8,000 |General VQA |
|
| 119 |
-
|spark |3,904 |3,904 |6,248 |65,982 |73,973 |General VQA |
|
| 120 |
-
|spatialsense |10,440 |10,440 |17,498 |200,963 |418,883 |General VQA |
|
| 121 |
-
|spot_the_diff |17,132 |8,566 |9,524 |82,670 |209,630 |General VQA |
|
| 122 |
-
|vision_flan(filtered) |175,964 |175,964 |175,964 |9,983,758 |3,009,891 |General VQA |
|
| 123 |
-
|visual7w |14,366 |14,366 |69,817 |3,054,334 |209,451 |General VQA |
|
| 124 |
-
|vizwiz(mathv360k) |6,604 |6,604 |6,604 |197,143 |44,876 |General VQA |
|
| 125 |
-
|vqav2 |82,772 |82,772 |443,757 |5,722,488 |1,100,837 |General VQA |
|
| 126 |
-
|vsr |2,157 |2,157 |3,354 |79,596 |6,708 |General VQA |
|
| 127 |
-
|websight |10,000 |10,000 |10,000 |113,114 |5,237,381 |General VQA |
|
| 128 |
-
|wildvision |333 |333 |405 |50,161 |72,820 |General VQA |
|
| 129 |
-
|yesbut |4,318 |4,318 |4,318 |38,365 |157,229 |General VQA |
|
| 130 |
-
|aguvis-stage-1 |458,957 |458,957 |3,831,666 |36,151,272 |93,546,182 |Grounding & Counting |
|
| 131 |
-
|groundui |13,531 |13,531 |18,016 |200,094 |883,274 |Grounding & Counting |
|
| 132 |
-
|
|
| 133 |
-
|oodvqa |8,488 |8,488 |8,488 |227,028 |8,488 |Grounding & Counting |
|
| 134 |
-
|tallyqa |98,680 |98,680 |183,986 |2,674,306 |370,282 |Grounding & Counting |
|
| 135 |
-
|clevr |70,000 |70,000 |699,989 |19,277,813 |1,570,525 |Mathematics |
|
| 136 |
-
|clevr_math |70,000 |70,000 |556,082 |7,888,064 |580,324 |Mathematics |
|
| 137 |
-
|clevr_math(mathv360k) |5,280 |5,280 |5,280 |174,879 |27,536 |Mathematics |
|
| 138 |
-
|CoSyn_400k_math |66,714 |66,714 |66,714 |500,554 |28,631,388 |Mathematics |
|
| 139 |
-
|geo170k(align) |35,297 |35,297 |35,297 |336,151 |1,866,019 |Mathematics |
|
| 140 |
-
|geo170k(qa) |12,101 |12,101 |12,101 |1,254,831 |1,115,242 |Mathematics |
|
| 141 |
-
|geo3k |2,091 |2,091 |2,091 |130,287 |2,091 |Mathematics |
|
| 142 |
-
|geometry3k(mathv360k) |9,724 |9,724 |9,724 |541,908 |69,075 |Mathematics |
|
| 143 |
-
|geomverse |9,303 |9,303 |9,339 |662,756 |2,454,014 |Mathematics |
|
| 144 |
-
|geoqa+(mathv360k) |17,162 |17,162 |17,162 |1,449,094 |117,740 |Mathematics |
|
| 145 |
-
|geos(mathv360k) |498 |498 |498 |32,394 |3,509 |Mathematics |
|
| 146 |
-
|intergps |1,280 |1,280 |1,760 |97,799 |5,280 |Mathematics |
|
| 147 |
-
|mavis_math_metagen |87,348 |87,348 |87,348 |6,668,920 |5,486,485 |Mathematics |
|
| 148 |
-
|mavis_math_rule_geo |99,986 |99,986 |99,986 |8,211,079 |12,535,251 |Mathematics |
|
| 149 |
-
|raven |63,081 |42,000 |42,000 |584,843 |63,081 |Mathematics |
|
| 150 |
-
|super_clevr(mathv360k) |8,642 |8,642 |8,642 |307,438 |44,129 |Mathematics |
|
| 151 |
-
|unigeo(mathv360k) |11,949 |11,949 |11,949 |1,011,069 |81,781 |Mathematics |
|
| 152 |
-
|art |5,603 |5,603 |5,603 |56,573 |283,138 |Naive OCR |
|
| 153 |
-
|captcha |113,062 |113,062 |113,062 |1,469,548 |466,856 |Naive OCR |
|
| 154 |
-
|chrome_writting |8,825 |8,825 |8,825 |150,025 |172,940 |Naive OCR |
|
| 155 |
-
|cocotext |16,169 |16,169 |16,169 |143,818 |177,111 |Naive OCR |
|
| 156 |
-
|ctw |24,290 |24,290 |180,621 |9,787,485 |1,653,254 |Naive OCR |
|
| 157 |
-
|funsd |194 |194 |3,879 |16,856 |29,996 |Naive OCR |
|
| 158 |
-
|hme100k |74,492 |74,492 |74,492 |1,117,380 |1,757,743 |Naive OCR |
|
| 159 |
-
|hw_squad |20,457 |20,457 |83,682 |1,071,534 |388,518 |Naive OCR |
|
| 160 |
-
|iam |5,663 |5,663 |5,663 |45,582 |130,794 |Naive OCR |
|
| 161 |
-
|iiit5k |1,990 |1,990 |1,990 |35,820 |4,259 |Naive OCR |
|
| 162 |
-
|imgur5k |5,934 |5,934 |5,934 |89,010 |288,054 |Naive OCR |
|
| 163 |
-
|k12_printing |256,636 |256,636 |256,636 |14,114,980 |7,465,001 |Naive OCR |
|
| 164 |
-
|latex_handwritten |39,583 |39,583 |39,583 |390,343 |1,874,733 |Naive OCR |
|
| 165 |
-
|latexformulas |552,340 |552,340 |552,340 |5,138,603 |43,094,747 |Naive OCR |
|
| 166 |
-
|maptext |200 |200 |799 |9,434 |70,813 |Naive OCR |
|
| 167 |
-
|mathwriting-google |300,000 |300,000 |300,000 |2,461,270 |5,954,806 |Naive OCR |
|
| 168 |
-
|memotion |6,991 |6,991 |6,991 |194,718 |177,429 |Naive OCR |
|
| 169 |
-
|orand_car_a |1,999 |1,999 |1,999 |43,978 |9,035 |Naive OCR |
|
| 170 |
-
|rendered_text |10,000 |10,000 |10,000 |85,879 |244,183 |Naive OCR |
|
| 171 |
-
|sroie |33,616 |33,616 |33,616 |605,088 |243,240 |Naive OCR |
|
| 172 |
-
|svrd |4,396 |4,396 |4,396 |65,400 |834,514 |Naive OCR |
|
| 173 |
-
|SynthCodeNet |499,983 |499,983 |499,983 |2,000,683 |253,422,136 |Naive OCR |
|
| 174 |
-
|synthdog |500,000 |500,000 |500,000 |8,849,848 |48,010,145 |Naive OCR |
|
| 175 |
-
|SynthFormulaNet |499,997 |499,997 |499,997 |1,999,631 |51,215,097 |Naive OCR |
|
| 176 |
-
|tal_ocr_eng |256,646 |256,646 |256,646 |3,385,012 |7,465,207 |Naive OCR |
|
| 177 |
-
|wordart |19,066 |4,804 |4,804 |78,032 |54,263 |Naive OCR |
|
| 178 |
-
|olmOCR-mix-0225-documents |228,864 |228,864 |228,858 |2,197,147 |163,194,337 |Naive OCR |
|
| 179 |
-
|olmOCR-mix-0225-books |15,194 |15,194 |15,194 |145,750 |7,962,779 |Naive OCR |
|
| 180 |
-
|a_okvqa |54,602 |54,602 |54,602 |1,065,188 |360,990 |OCR QA |
|
| 181 |
-
|aokvqa |16,539 |16,539 |17,056 |743,458 |218,917 |OCR QA |
|
| 182 |
-
|arxivqa |100,000 |100,000 |100,000 |7,022,001 |6,422,269 |OCR QA |
|
| 183 |
-
|bentham |10,843 |10,843 |10,843 |103,042 |124,459 |OCR QA |
|
| 184 |
-
|blockdiagramcomputerized |502 |502 |502 |5,067 |34,453 |OCR QA |
|
| 185 |
-
|blockdiagramhandwritten |1,029 |1,029 |1,029 |11,444 |75,598 |OCR QA |
|
| 186 |
-
|CoSyn_400k_diagram |34,963 |34,963 |300,357 |3,356,844 |11,943,321 |OCR QA |
|
| 187 |
-
|CoSyn_400k_document |71,282 |71,282 |605,173 |6,216,517 |16,095,526 |OCR QA |
|
| 188 |
-
|CoSyn_400k_music |11,969 |11,969 |81,786 |792,129 |3,175,586 |OCR QA |
|
| 189 |
-
|CoSyn_400k_nutrition |6,931 |6,931 |112,097 |1,642,936 |3,687,254 |OCR QA |
|
| 190 |
-
|diagram_image_to_text |300 |300 |300 |3,631 |20,723 |OCR QA |
|
| 191 |
-
|DoclingMatix |2,465,202 |1,270,911 |10,626,898 |162,581,660 |2,996,338,775 |OCR QA |
|
| 192 |
-
|docvqa |10,189 |10,189 |39,463 |724,814 |275,510 |OCR QA |
|
| 193 |
-
|est_vqa |19,358 |19,358 |19,358 |286,343 |143,270 |OCR QA |
|
| 194 |
-
|handwriting_forms |1,400 |1,400 |1,400 |81,200 |41,490 |OCR QA |
|
| 195 |
-
|infographic_vqa |1,982 |4,394 |23,717 |392,456 |86,951 |OCR QA |
|
| 196 |
-
|infographic_vqa_llava_format |4,394 |2,113 |10,054 |174,352 |43,912 |OCR QA |
|
| 197 |
-
|infographic(gpt4v) |2,113 |1,982 |1,982 |275,498 |1,044,183 |OCR QA |
|
| 198 |
-
|invoices_receipts |3,013 |3,013 |3,013 |36,745 |771,948 |OCR QA |
|
| 199 |
-
|mapqa |37,417 |37,417 |483,416 |8,454,722 |5,657,339 |OCR QA |
|
| 200 |
-
|mapqa(mathv360k) |5,225 |5,225 |5,225 |168,390 |44,560 |OCR QA |
|
| 201 |
-
|mmsoc_memotion |6,991 |6,991 |6,991 |188,505 |421,250 |OCR QA |
|
| 202 |
-
|ocrvqa |165,746 |165,746 |801,579 |12,217,564 |4,801,833 |OCR QA |
|
| 203 |
-
|pdfvqa |8,593 |8,593 |95,000 |1,272,618 |939,948 |OCR QA |
|
| 204 |
-
|screen2words |15,730 |15,730 |15,743 |133,014 |120,781 |OCR QA |
|
| 205 |
-
|screenqa |80,761 |80,761 |80,761 |940,729 |826,795 |OCR QA |
|
| 206 |
-
|slidevqa |11,868 |1,919 |10,617 |333,065 |156,036 |OCR QA |
|
| 207 |
-
|st_vqa |17,247 |17,247 |23,121 |338,837 |98,892 |OCR QA |
|
| 208 |
-
|sujet_finance |9,801 |9,801 |107,050 |1,395,624 |1,925,361 |OCR QA |
|
| 209 |
-
|textocr(gpt4v) |25,060 |25,060 |25,060 |150,360 |2,436,974 |OCR QA |
|
| 210 |
-
|textvqa |21,953 |21,953 |34,602 |553,990 |141,882 |OCR QA |
|
| 211 |
-
|ureader_cap |91,215 |91,215 |91,215 |1,086,484 |1,435,964 |OCR QA |
|
| 212 |
-
|ureader_ie |17,320 |17,320 |17,320 |406,237 |128,229 |OCR QA |
|
| 213 |
-
|ureader_kg_processed |37,550 |37,550 |37,550 |352,907 |2,013,731 |OCR QA |
|
| 214 |
-
|ureader_qa_processed |252,953 |252,953 |252,953 |7,100,750 |930,617 |OCR QA |
|
| 215 |
-
|visualmrc |3,027 |3,027 |11,988 |139,751 |147,385 |OCR QA |
|
| 216 |
-
|ai2d_merged |4,858 |4,858 |12,325 |755,455 |1,319,140 |Science |
|
| 217 |
-
|CoSyn_400k_chemical |8,942 |8,942 |55,391 |634,881 |2,450,290 |Science |
|
| 218 |
-
|CoSyn_400k_circuit |10,470 |10,470 |67,939 |713,575 |2,637,618 |Science |
|
| 219 |
-
|pathvqa |32,632 |32,632 |32,632 |639,385 |85,168 |Science |
|
| 220 |
-
|pmc_vqa(mathv360k) |35,948 |35,948 |35,948 |1,889,167 |255,109 |Science |
|
| 221 |
-
|scienceqa |4,976 |4,976 |6,149 |1,081,220 |18,447 |Science |
|
| 222 |
-
|scienceqa(nona_context) |19,208 |19,208 |19,208 |1,624,583 |25,311 |Science |
|
| 223 |
-
|tqa |2,749 |2,749 |12,567 |395,956 |149,776 |Science |
|
| 224 |
-
|visualwebinstruct(filtered) |263,581 |263,581 |263,581 |8,341,540 |31,802,459 |Science |
|
| 225 |
-
|vqarad |313 |313 |1,793 |25,181 |6,003 |Science |
|
| 226 |
-
|text_code_feedback |0 |66,383 |221,096 |19,349,056 |79,752,351 |Text-only |
|
| 227 |
-
|text_codefeedback_filtered_instruction|0 |156,525 |156,525 |27,684,170 |62,764,414 |Text-only |
|
| 228 |
-
|text_infinitymath |0 |101,380 |101,380 |9,158,132 |212,543 |Text-only |
|
| 229 |
-
|text_mathinstruct |0 |262,039 |262,039 |20,405,295 |44,145,362 |Text-only |
|
| 230 |
-
|text_mathqa |0 |394,996 |394,996 |23,552,035 |72,451,061 |Text-only |
|
| 231 |
-
|text_mathstepdpo10k |0 |10,795 |10,795 |557,233 |989,312 |Text-only |
|
| 232 |
-
|text_numinamath_cot |0 |859,494 |859,494 |75,818,870 |387,758,581 |Text-only |
|
| 233 |
-
|text_openhermes_2_5 |0 |1,001,551 |1,008,268 |142,376,960 |233,561,291 |Text-only |
|
| 234 |
-
|text_openorca |0 |4,233,853 |4,233,853 |1,049,478,873 |468,042,176 |Text-only |
|
| 235 |
-
|text_orcamath |0 |200,035 |200,035 |12,691,014 |61,860,987 |Text-only |
|
| 236 |
-
|text_pythoncode25k |0 |49,626 |49,626 |1,629,286 |4,945,892 |Text-only |
|
| 237 |
-
|text_pythoncodealpaca |0 |18,612 |18,612 |655,127 |2,683,469 |Text-only |
|
| 238 |
-
|text_ruozhiba |0 |1,496 |1,496 |69,795 |234,822 |Text-only |
|
| 239 |
-
|text_theoremqa |0 |800 |800 |50,065 |3,468 |Text-only |
|
| 240 |
-
|text_wizardlm_evol |0 |69,999 |69,999 |7,753,963 |21,955,856 |Text-only |
|
| 241 |
-
|text_OpenMathInstruct-2 |0 |1,000,000 |1,000,000 |74,905,850 |413,132,418 |Text-only |
|
|
|
|
| 242 |
</Accordion>
|
| 243 |
</Wide>
|
| 244 |
|
|
|
|
| 52 |
|
| 53 |
<Wide>
|
| 54 |
<Accordion title="FineVision Subsets">
|
| 55 |
+
|Subset Name |Total Images|Total Samples|Total Turns|Total Question Tokens|Total Answer Tokens|Category |Citation |
|
| 56 |
+
|--------------------------------------|------------|-------------|-----------|---------------------|-------------------|----------------------|-------------------------------------------------------------------|
|
| 57 |
+
|coco_colors |118,287 |118,287 |118,287 |1,301,157 |6,376,672 |Captioning & Knowledge|[@noauthor_hazal-karakusmscoco-controlnet-canny-less-colors_nodate]|
|
| 58 |
+
|densefusion_1m |1,058,751 |1,058,751 |1,058,751 |10,692,478 |263,718,217 |Captioning & Knowledge|[@li_densefusion-1m_2024] |
|
| 59 |
+
|face_emotion |797 |797 |797 |8,767 |8,066 |Captioning & Knowledge|[@mollahosseini_affectnet_2017] |
|
| 60 |
+
|google_landmarks |299,993 |299,993 |842,127 |6,194,978 |10,202,980 |Captioning & Knowledge| |
|
| 61 |
+
|image_textualization(filtered) |99,573 |99,573 |99,573 |917,577 |19,374,090 |Captioning & Knowledge|[@pi_image_2024] |
|
| 62 |
+
|laion_gpt4v |9,301 |9,301 |9,301 |93,950 |1,875,283 |Captioning & Knowledge|[@noauthor_laiongpt4v-dataset_2023] |
|
| 63 |
+
|localized_narratives |199,998 |199,998 |199,998 |2,167,179 |8,021,473 |Captioning & Knowledge|[@vedaldi_connecting_2020] |
|
| 64 |
+
|sharegpt4o |57,284 |57,284 |57,284 |558,647 |36,555,323 |Captioning & Knowledge|[@noauthor_sharegpt-4o_nodate] |
|
| 65 |
+
|sharegpt4v(coco) |50,017 |50,017 |50,017 |460,893 |9,825,387 |Captioning & Knowledge|[@leonardis_sharegpt4v_2025] |
|
| 66 |
+
|sharegpt4v(knowledge) |1,988 |1,988 |1,988 |18,250 |293,850 |Captioning & Knowledge|[@leonardis_sharegpt4v_2025] |
|
| 67 |
+
|sharegpt4v(llava) |29,986 |29,986 |29,986 |275,783 |6,175,899 |Captioning & Knowledge|[@leonardis_sharegpt4v_2025] |
|
| 68 |
+
|sharegpt4v(sam) |8,990 |8,990 |8,990 |82,874 |1,668,797 |Captioning & Knowledge|[@leonardis_sharegpt4v_2025] |
|
| 69 |
+
|textcaps |21,906 |21,906 |21,906 |240,966 |355,991 |Captioning & Knowledge|[@vedaldi_textcaps_2020] |
|
| 70 |
+
|chart2text |26,961 |26,961 |30,215 |342,215 |2,670,580 |Chart & Table |[@kantharaj_chart--text_2022] |
|
| 71 |
+
|chartqa |18,265 |18,265 |28,287 |625,569 |134,793 |Chart & Table |[@masry_chartqa_2022] |
|
| 72 |
+
|CoSyn_400k_chart |116,814 |116,814 |1,085,882 |17,617,591 |57,641,030 |Chart & Table |[@yang_scaling_2025] |
|
| 73 |
+
|CoSyn_400k_table |46,518 |46,518 |416,519 |6,280,455 |23,335,054 |Chart & Table |[@yang_scaling_2025] |
|
| 74 |
+
|dvqa |200,000 |200,000 |2,325,316 |44,603,372 |5,477,966 |Chart & Table |[@kafle_dvqa_2018] |
|
| 75 |
+
|figureqa |100,000 |100,000 |1,327,368 |18,515,153 |2,654,736 |Chart & Table |[@kahou_figureqa_2018] |
|
| 76 |
+
|figureqa(mathv360k) |17,587 |17,587 |17,587 |722,959 |97,404 |Chart & Table |[@shi_math-llava_2024] |
|
| 77 |
+
|finqa |5,276 |5,276 |6,251 |5,552,943 |224,015 |Chart & Table |[@chen_finqa_2022] |
|
| 78 |
+
|hitab |2,500 |2,500 |7,782 |177,999 |335,013 |Chart & Table |[@cheng_hitab_2022] |
|
| 79 |
+
|lrv_chart |1,776 |1,776 |5,372 |76,477 |158,711 |Chart & Table |[@noauthor_lmms-labllava-onevision-data_2025] |
|
| 80 |
+
|mmc_instruct |168,178 |168,178 |168,178 |50,008,824 |74,581,055 |Chart & Table |[@liu_mmc_2024] |
|
| 81 |
+
|multihiertt |30,875 |7,619 |7,830 |218,840 |244,744 |Chart & Table |[@zhao_multihiertt_2022] |
|
| 82 |
+
|plotqa |157,070 |157,070 |20,249,479 |738,371,054 |118,122,387 |Chart & Table |[@methani_plotqa_2020] |
|
| 83 |
+
|robut_sqa |8,514 |8,514 |34,141 |368,957 |1,794,570 |Chart & Table |[@zhao_robut_2023] |
|
| 84 |
+
|robut_wikisql |74,989 |74,989 |86,202 |1,454,920 |9,276,100 |Chart & Table |[@zhao_robut_2023] |
|
| 85 |
+
|robut_wtq |38,246 |38,246 |44,096 |587,040 |6,415,830 |Chart & Table |[@zhao_robut_2023] |
|
| 86 |
+
|SynthChartNet |500,000 |500,000 |500,000 |2,169,240 |67,392,223 |Chart & Table |[@nassar_smoldocling_2025] |
|
| 87 |
+
|tabmwp |22,722 |22,722 |23,021 |639,639 |1,883,243 |Chart & Table |[@lu_dynamic_2023] |
|
| 88 |
+
|tabmwp(mathv360k) |22,452 |22,452 |22,452 |963,498 |158,042 |Chart & Table |[@shi_math-llava_2024] |
|
| 89 |
+
|tat_dqa |2,448 |2,207 |13,251 |320,356 |1,177,852 |Chart & Table |[@zhu_towards_2022] |
|
| 90 |
+
|tat_qa |2,199 |2,199 |13,215 |989,419 |254,790 |Chart & Table |[@zhu_tat-qa_2021] |
|
| 91 |
+
|Unichart |611,925 |611,925 |6,898,324 |96,702,288 |211,989,247 |Chart & Table |[@masry_unichart_2023] |
|
| 92 |
+
|vistext |9,969 |9,969 |9,969 |88,770 |1,191,127 |Chart & Table |[@tang_vistext_2023] |
|
| 93 |
+
|vqaonbd |39,986 |39,986 |1,254,165 |36,066,807 |5,620,523 |Chart & Table |[@noauthor_jp1924vqaonbd_nodate] |
|
| 94 |
+
|alfworldgpt |45,073 |45,073 |45,073 |17,864,033 |6,276,573 |General VQA |[@shridhar_alfworld_2021] |
|
| 95 |
+
|allava_laion |468,664 |468,664 |937,328 |18,654,303 |145,799,426 |General VQA |[@chen_allava_2024] |
|
| 96 |
+
|allava_vflan |177,078 |177,078 |387,872 |12,444,711 |55,305,642 |General VQA |[@chen_allava_2024] |
|
| 97 |
+
|cambrian(filtered)_processed |83,123 |83,124 |98,534 |1,410,321 |5,503,211 |General VQA |[@tong_cambrian-1_2024] |
|
| 98 |
+
|chinesememe |54,212 |54,212 |54,212 |538,938 |21,122,723 |General VQA |[@noauthor_reilxchinese-meme-description-dataset_2024] |
|
| 99 |
+
|cocoqa |46,287 |46,287 |78,736 |1,136,238 |212,480 |General VQA |[@ren_exploring_2015] |
|
| 100 |
+
|CoSyn_400k_graphic |26,968 |26,968 |26,968 |1,678,862 |8,235,679 |General VQA |[@yang_scaling_2025] |
|
| 101 |
+
|datik |220,537 |222,385 |222,385 |2,234,054 |187,757,952 |General VQA |[@belouadi_automatikz_2024] |
|
| 102 |
+
|datikz |47,441 |47,974 |48,296 |441,040 |59,116,193 |General VQA |[@belouadi_automatikz_2024] |
|
| 103 |
+
|drivelm |90,049 |4,072 |161,030 |2,399,362 |1,431,417 |General VQA |[@leonardis_drivelm_2025] |
|
| 104 |
+
|hateful_memes |8,500 |8,500 |8,500 |128,375 |17,000 |General VQA |[@kiela_hateful_2020] |
|
| 105 |
+
|iconqa |27,307 |27,307 |29,841 |906,877 |72,492 |General VQA |[@lu_iconqa_2022] |
|
| 106 |
+
|iconqa(mathv360k) |22,589 |22,589 |22,589 |952,183 |134,029 |General VQA |[@shi_math-llava_2024] |
|
| 107 |
+
|idk |11,123 |11,123 |27,614 |235,262 |665,247 |General VQA |[@cha_visually_2024] |
|
| 108 |
+
|indoor_qa |3,350 |3,350 |3,350 |36,832 |19,700 |General VQA | |
|
| 109 |
+
|LLaVA_Instruct_150K |157,710 |157,710 |361,405 |4,412,600 |28,719,278 |General VQA |[@liu_visual_2023] |
|
| 110 |
+
|llavar_gpt4_20k |19,790 |19,790 |43,167 |546,703 |1,516,730 |General VQA |[@zhang_llavar_2024] |
|
| 111 |
+
|lnqa |302,780 |302,780 |1,520,942 |16,530,323 |19,027,663 |General VQA |[@noauthor_viks_nodate] |
|
| 112 |
+
|lrv_normal(filtered) |10,489 |10,489 |155,269 |2,108,321 |3,134,247 |General VQA |[@liu_mitigating_2024] |
|
| 113 |
+
|lvis_instruct4v |222,711 |222,711 |1,050,622 |12,556,173 |43,726,782 |General VQA |[@wang_see_2023] |
|
| 114 |
+
|mimic_cgd |141,878 |70,939 |141,869 |1,789,740 |4,304,380 |General VQA |[@li_mimic-it_2023] |
|
| 115 |
+
|mmevol |160,215 |160,215 |630,441 |16,203,127 |50,445,237 |General VQA |[@luo_mmevol_2024] |
|
| 116 |
+
|mmra |2,048 |1,024 |1,024 |72,523 |25,764 |General VQA |[@wu_mmra_2024] |
|
| 117 |
+
|nlvr2 |100,852 |50,426 |86,373 |4,629,641 |172,746 |General VQA |[@suhr_corpus_2019] |
|
| 118 |
+
|sketchyvqa |8,000 |8,000 |8,000 |182,192 |8,000 |General VQA |[@tu_how_2023] |
|
| 119 |
+
|spark |3,904 |3,904 |6,248 |65,982 |73,973 |General VQA |[@yu_spark_2024] |
|
| 120 |
+
|spatialsense |10,440 |10,440 |17,498 |200,963 |418,883 |General VQA |[@yang_spatialsense_2019] |
|
| 121 |
+
|spot_the_diff |17,132 |8,566 |9,524 |82,670 |209,630 |General VQA |[@jhamtani_learning_2018] |
|
| 122 |
+
|vision_flan(filtered) |175,964 |175,964 |175,964 |9,983,758 |3,009,891 |General VQA |[@xu_vision-flan_2024] |
|
| 123 |
+
|visual7w |14,366 |14,366 |69,817 |3,054,334 |209,451 |General VQA |[@zhu_visual7w_2016] |
|
| 124 |
+
|vizwiz(mathv360k) |6,604 |6,604 |6,604 |197,143 |44,876 |General VQA |[@gurari_vizwiz_2018] |
|
| 125 |
+
|vqav2 |82,772 |82,772 |443,757 |5,722,488 |1,100,837 |General VQA |[@goyal_making_2017] |
|
| 126 |
+
|vsr |2,157 |2,157 |3,354 |79,596 |6,708 |General VQA |[@liu_visual_2023-1] |
|
| 127 |
+
|websight |10,000 |10,000 |10,000 |113,114 |5,237,381 |General VQA |[@laurencon_unlocking_2024] |
|
| 128 |
+
|wildvision |333 |333 |405 |50,161 |72,820 |General VQA |[@lu_wildvision_2024] |
|
| 129 |
+
|yesbut |4,318 |4,318 |4,318 |38,365 |157,229 |General VQA |[@nandy_yesbut_2024] |
|
| 130 |
+
|aguvis-stage-1 |458,957 |458,957 |3,831,666 |36,151,272 |93,546,182 |Grounding & Counting |[@xu_aguvis_2025] |
|
| 131 |
+
|groundui |13,531 |13,531 |18,016 |200,094 |883,274 |Grounding & Counting |[@zheng_agentstudio_2025] |
|
| 132 |
+
|objects365_qa |1,742,287 |1,742,287 |12,329,259 |135,681,680 |2,146,619,635 |Grounding & Counting |[@shao_objects365_2019] |
|
| 133 |
+
|oodvqa |8,488 |8,488 |8,488 |227,028 |8,488 |Grounding & Counting |[@tu_how_2023] |
|
| 134 |
+
|tallyqa |98,680 |98,680 |183,986 |2,674,306 |370,282 |Grounding & Counting |[@acharya_tallyqa_2019] |
|
| 135 |
+
|clevr |70,000 |70,000 |699,989 |19,277,813 |1,570,525 |Mathematics |[@lindstrom_clevr-math_2022-1] |
|
| 136 |
+
|clevr_math |70,000 |70,000 |556,082 |7,888,064 |580,324 |Mathematics |[@shi_math-llava_2024] |
|
| 137 |
+
|clevr_math(mathv360k) |5,280 |5,280 |5,280 |174,879 |27,536 |Mathematics |[@shi_math-llava_2024] |
|
| 138 |
+
|CoSyn_400k_math |66,714 |66,714 |66,714 |500,554 |28,631,388 |Mathematics |[@yang_scaling_2025] |
|
| 139 |
+
|geo170k(align) |35,297 |35,297 |35,297 |336,151 |1,866,019 |Mathematics |[@gao_g-llava_2025] |
|
| 140 |
+
|geo170k(qa) |12,101 |12,101 |12,101 |1,254,831 |1,115,242 |Mathematics |[@gao_g-llava_2025] |
|
| 141 |
+
|geo3k |2,091 |2,091 |2,091 |130,287 |2,091 |Mathematics |[@lu_inter-gps_2021] |
|
| 142 |
+
|geometry3k(mathv360k) |9,724 |9,724 |9,724 |541,908 |69,075 |Mathematics |[@shi_math-llava_2024] |
|
| 143 |
+
|geomverse |9,303 |9,303 |9,339 |662,756 |2,454,014 |Mathematics |[@kazemi_geomverse_2023] |
|
| 144 |
+
|geoqa+(mathv360k) |17,162 |17,162 |17,162 |1,449,094 |117,740 |Mathematics |[@cao_augmented_2022] |
|
| 145 |
+
|geos(mathv360k) |498 |498 |498 |32,394 |3,509 |Mathematics |[@seo_solving_2015] |
|
| 146 |
+
|intergps |1,280 |1,280 |1,760 |97,799 |5,280 |Mathematics |[@lu_inter-gps_2021-1] |
|
| 147 |
+
|mavis_math_metagen |87,348 |87,348 |87,348 |6,668,920 |5,486,485 |Mathematics |[@zhang_mavis_2024] |
|
| 148 |
+
|mavis_math_rule_geo |99,986 |99,986 |99,986 |8,211,079 |12,535,251 |Mathematics |[@zhang_mavis_2024] |
|
| 149 |
+
|raven |63,081 |42,000 |42,000 |584,843 |63,081 |Mathematics |[@zhang_raven_2019] |
|
| 150 |
+
|super_clevr(mathv360k) |8,642 |8,642 |8,642 |307,438 |44,129 |Mathematics |[@shi_math-llava_2024] |
|
| 151 |
+
|unigeo(mathv360k) |11,949 |11,949 |11,949 |1,011,069 |81,781 |Mathematics |[@shi_math-llava_2024] |
|
| 152 |
+
|art |5,603 |5,603 |5,603 |56,573 |283,138 |Naive OCR |[@chng_icdar2019_2019] |
|
| 153 |
+
|captcha |113,062 |113,062 |113,062 |1,469,548 |466,856 |Naive OCR | |
|
| 154 |
+
|chrome_writting |8,825 |8,825 |8,825 |150,025 |172,940 |Naive OCR |[@mouchere_icdar_2013] |
|
| 155 |
+
|cocotext |16,169 |16,169 |16,169 |143,818 |177,111 |Naive OCR |[@veit_coco-text_2016] |
|
| 156 |
+
|ctw |24,290 |24,290 |180,621 |9,787,485 |1,653,254 |Naive OCR |[@yuan_large_2019] |
|
| 157 |
+
|funsd |194 |194 |3,879 |16,856 |29,996 |Naive OCR |[@jaume_funsd_2019] |
|
| 158 |
+
|hme100k |74,492 |74,492 |74,492 |1,117,380 |1,757,743 |Naive OCR |[@yuan_syntax-aware_2022] |
|
| 159 |
+
|hw_squad |20,457 |20,457 |83,682 |1,071,534 |388,518 |Naive OCR |[@mathew_asking_2021] |
|
| 160 |
+
|iam |5,663 |5,663 |5,663 |45,582 |130,794 |Naive OCR |[@marti_iam-database_2002] |
|
| 161 |
+
|iiit5k |1,990 |1,990 |1,990 |35,820 |4,259 |Naive OCR |[@mishra_scene_2012] |
|
| 162 |
+
|imgur5k |5,934 |5,934 |5,934 |89,010 |288,054 |Naive OCR |[@krishnan_textstylebrush_2023] |
|
| 163 |
+
|k12_printing |256,636 |256,636 |256,636 |14,114,980 |7,465,001 |Naive OCR |[@noauthor_lmms-labllava-onevision-data_2025] |
|
| 164 |
+
|latex_handwritten |39,583 |39,583 |39,583 |390,343 |1,874,733 |Naive OCR |[@noauthor_im2latex_nodate] |
|
| 165 |
+
|latexformulas |552,340 |552,340 |552,340 |5,138,603 |43,094,747 |Naive OCR |[@noauthor_oleehyolatex-formulas_2024] |
|
| 166 |
+
|maptext |200 |200 |799 |9,434 |70,813 |Naive OCR |[@barney_smith_icdar_2024] |
|
| 167 |
+
|mathwriting-google |300,000 |300,000 |300,000 |2,461,270 |5,954,806 |Naive OCR |[@gervais_mathwriting_2025] |
|
| 168 |
+
|memotion |6,991 |6,991 |6,991 |194,718 |177,429 |Naive OCR |[@sharma_semeval-2020_2020] |
|
| 169 |
+
|orand_car_a |1,999 |1,999 |1,999 |43,978 |9,035 |Naive OCR |[@diem_icfhr_2014] |
|
| 170 |
+
|rendered_text |10,000 |10,000 |10,000 |85,879 |244,183 |Naive OCR |[@noauthor_wendlercrenderedtext_2024] |
|
| 171 |
+
|sroie |33,616 |33,616 |33,616 |605,088 |243,240 |Naive OCR |[@huang_icdar2019_2019] |
|
| 172 |
+
|svrd |4,396 |4,396 |4,396 |65,400 |834,514 |Naive OCR |[@fink_icdar_2023] |
|
| 173 |
+
|SynthCodeNet |499,983 |499,983 |499,983 |2,000,683 |253,422,136 |Naive OCR |[@nassar_smoldocling_2025] |
|
| 174 |
+
|synthdog |500,000 |500,000 |500,000 |8,849,848 |48,010,145 |Naive OCR |[@avidan_ocr-free_2022] |
|
| 175 |
+
|SynthFormulaNet |499,997 |499,997 |499,997 |1,999,631 |51,215,097 |Naive OCR |[@nassar_smoldocling_2025] |
|
| 176 |
+
|tal_ocr_eng |256,646 |256,646 |256,646 |3,385,012 |7,465,207 |Naive OCR |[@noauthor_httpsai100talcomdataset_nodate] |
|
| 177 |
+
|wordart |19,066 |4,804 |4,804 |78,032 |54,263 |Naive OCR |[@avidan_toward_2022] |
|
| 178 |
+
|olmOCR-mix-0225-documents |228,864 |228,864 |228,858 |2,197,147 |163,194,337 |Naive OCR |[@poznanski_olmocr_2025] |
|
| 179 |
+
|olmOCR-mix-0225-books |15,194 |15,194 |15,194 |145,750 |7,962,779 |Naive OCR |[@poznanski_olmocr_2025] |
|
| 180 |
+
|a_okvqa |54,602 |54,602 |54,602 |1,065,188 |360,990 |OCR QA |[@avidan_-okvqa_2022] |
|
| 181 |
+
|aokvqa |16,539 |16,539 |17,056 |743,458 |218,917 |OCR QA |[@avidan_-okvqa_2022] |
|
| 182 |
+
|arxivqa |100,000 |100,000 |100,000 |7,022,001 |6,422,269 |OCR QA |[@li_multimodal_2024] |
|
| 183 |
+
|bentham |10,843 |10,843 |10,843 |103,042 |124,459 |OCR QA |[@mathew_asking_2021] |
|
| 184 |
+
|blockdiagramcomputerized |502 |502 |502 |5,067 |34,453 |OCR QA |[@bhushan_block_2022] |
|
| 185 |
+
|blockdiagramhandwritten |1,029 |1,029 |1,029 |11,444 |75,598 |OCR QA |[@bhushan_block_2022] |
|
| 186 |
+
|CoSyn_400k_diagram |34,963 |34,963 |300,357 |3,356,844 |11,943,321 |OCR QA |[@yang_scaling_2025] |
|
| 187 |
+
|CoSyn_400k_document |71,282 |71,282 |605,173 |6,216,517 |16,095,526 |OCR QA |[@yang_scaling_2025] |
|
| 188 |
+
|CoSyn_400k_music |11,969 |11,969 |81,786 |792,129 |3,175,586 |OCR QA |[@yang_scaling_2025] |
|
| 189 |
+
|CoSyn_400k_nutrition |6,931 |6,931 |112,097 |1,642,936 |3,687,254 |OCR QA |[@yang_scaling_2025] |
|
| 190 |
+
|diagram_image_to_text |300 |300 |300 |3,631 |20,723 |OCR QA |[@noauthor_kamizuru00diagram_image_to_text_2024] |
|
| 191 |
+
|DoclingMatix |2,465,202 |1,270,911 |10,626,898 |162,581,660 |2,996,338,775 |OCR QA |[@nassar_smoldocling_2025] |
|
| 192 |
+
|docvqa |10,189 |10,189 |39,463 |724,814 |275,510 |OCR QA |[@mathew_docvqa_2021] |
|
| 193 |
+
|est_vqa |19,358 |19,358 |19,358 |286,343 |143,270 |OCR QA |[@wang_general_2020] |
|
| 194 |
+
|handwriting_forms |1,400 |1,400 |1,400 |81,200 |41,490 |OCR QA |[@noauthor_ifthandwriting_forms_nodate] |
|
| 195 |
+
|infographic_vqa |1,982 |4,394 |23,717 |392,456 |86,951 |OCR QA |[@mathew_infographicvqa_2022] |
|
| 196 |
+
|infographic_vqa_llava_format |4,394 |2,113 |10,054 |174,352 |43,912 |OCR QA |[@mathew_infographicvqa_2022] |
|
| 197 |
+
|infographic(gpt4v) |2,113 |1,982 |1,982 |275,498 |1,044,183 |OCR QA |[@mathew_infographicvqa_2022] |
|
| 198 |
+
|invoices_receipts |3,013 |3,013 |3,013 |36,745 |771,948 |OCR QA |[@noauthor_mychen76invoices-and-receipts_ocr_v1_2025] |
|
| 199 |
+
|mapqa |37,417 |37,417 |483,416 |8,454,722 |5,657,339 |OCR QA |[@chang_mapqa_2022] |
|
| 200 |
+
|mapqa(mathv360k) |5,225 |5,225 |5,225 |168,390 |44,560 |OCR QA |[@shi_math-llava_2024] |
|
| 201 |
+
|mmsoc_memotion |6,991 |6,991 |6,991 |188,505 |421,250 |OCR QA |[@sharma_task_2020] |
|
| 202 |
+
|ocrvqa |165,746 |165,746 |801,579 |12,217,564 |4,801,833 |OCR QA |[@mishra_ocr-vqa_2019] |
|
| 203 |
+
|pdfvqa |8,593 |8,593 |95,000 |1,272,618 |939,948 |OCR QA |[@de_francisci_morales_pdf-vqa_2023] |
|
| 204 |
+
|screen2words |15,730 |15,730 |15,743 |133,014 |120,781 |OCR QA |[@wang_screen2words_2021] |
|
| 205 |
+
|screenqa |80,761 |80,761 |80,761 |940,729 |826,795 |OCR QA |[@hsiao_screenqa_2025] |
|
| 206 |
+
|slidevqa |11,868 |1,919 |10,617 |333,065 |156,036 |OCR QA |[@tanaka_slidevqa_2023] |
|
| 207 |
+
|st_vqa |17,247 |17,247 |23,121 |338,837 |98,892 |OCR QA |[@biten_scene_2019] |
|
| 208 |
+
|sujet_finance |9,801 |9,801 |107,050 |1,395,624 |1,925,361 |OCR QA |[@noauthor_sujet-aisujet-finance-qa-vision-100k_2024] |
|
| 209 |
+
|textocr(gpt4v) |25,060 |25,060 |25,060 |150,360 |2,436,974 |OCR QA |[@noauthor_jimmycartertextocr-gpt4v_2024] |
|
| 210 |
+
|textvqa |21,953 |21,953 |34,602 |553,990 |141,882 |OCR QA |[@singh_towards_2019] |
|
| 211 |
+
|ureader_cap |91,215 |91,215 |91,215 |1,086,484 |1,435,964 |OCR QA |[@ye_ureader_2023] |
|
| 212 |
+
|ureader_ie |17,320 |17,320 |17,320 |406,237 |128,229 |OCR QA |[@ye_ureader_2023] |
|
| 213 |
+
|ureader_kg_processed |37,550 |37,550 |37,550 |352,907 |2,013,731 |OCR QA |[@ye_ureader_2023] |
|
| 214 |
+
|ureader_qa_processed |252,953 |252,953 |252,953 |7,100,750 |930,617 |OCR QA |[@ye_ureader_2023] |
|
| 215 |
+
|visualmrc |3,027 |3,027 |11,988 |139,751 |147,385 |OCR QA |[@tanaka_visualmrc_2021] |
|
| 216 |
+
|ai2d_merged |4,858 |4,858 |12,325 |755,455 |1,319,140 |Science |[@noauthor_anditoai2d-merged_nodate] |
|
| 217 |
+
|CoSyn_400k_chemical |8,942 |8,942 |55,391 |634,881 |2,450,290 |Science |[@yang_scaling_2025] |
|
| 218 |
+
|CoSyn_400k_circuit |10,470 |10,470 |67,939 |713,575 |2,637,618 |Science |[@yang_scaling_2025] |
|
| 219 |
+
|pathvqa |32,632 |32,632 |32,632 |639,385 |85,168 |Science |[@he_pathvqa_2020] |
|
| 220 |
+
|pmc_vqa(mathv360k) |35,948 |35,948 |35,948 |1,889,167 |255,109 |Science |[@shi_math-llava_2024] |
|
| 221 |
+
|scienceqa |4,976 |4,976 |6,149 |1,081,220 |18,447 |Science |[@lu_learn_2022] |
|
| 222 |
+
|scienceqa(nona_context) |19,208 |19,208 |19,208 |1,624,583 |25,311 |Science |[@noauthor_lmms-labllava-onevision-data_2025] |
|
| 223 |
+
|tqa |2,749 |2,749 |12,567 |395,956 |149,776 |Science |[@kembhavi_are_2017] |
|
| 224 |
+
|visualwebinstruct(filtered) |263,581 |263,581 |263,581 |8,341,540 |31,802,459 |Science |[@jia_visualwebinstruct_2025] |
|
| 225 |
+
|vqarad |313 |313 |1,793 |25,181 |6,003 |Science |[@lau_dataset_2018] |
|
| 226 |
+
|text_code_feedback |0 |66,383 |221,096 |19,349,056 |79,752,351 |Text-only |[@zheng_opencodeinterpreter_2025] |
|
| 227 |
+
|text_codefeedback_filtered_instruction|0 |156,525 |156,525 |27,684,170 |62,764,414 |Text-only |[@zheng_opencodeinterpreter_2025] |
|
| 228 |
+
|text_infinitymath |0 |101,380 |101,380 |9,158,132 |212,543 |Text-only |[@zhang_infinity_2024] |
|
| 229 |
+
|text_mathinstruct |0 |262,039 |262,039 |20,405,295 |44,145,362 |Text-only |[@yue_mammoth_2023] |
|
| 230 |
+
|text_mathqa |0 |394,996 |394,996 |23,552,035 |72,451,061 |Text-only |[@amini_mathqa_2019] |
|
| 231 |
+
|text_mathstepdpo10k |0 |10,795 |10,795 |557,233 |989,312 |Text-only |[@lai_step-dpo_2024] |
|
| 232 |
+
|text_numinamath_cot |0 |859,494 |859,494 |75,818,870 |387,758,581 |Text-only |[@noauthor_ai-monuminamath-cot_2025] |
|
| 233 |
+
|text_openhermes_2_5 |0 |1,001,551 |1,008,268 |142,376,960 |233,561,291 |Text-only |[@noauthor_tekniumopenhermes-25_2024] |
|
| 234 |
+
|text_openorca |0 |4,233,853 |4,233,853 |1,049,478,873 |468,042,176 |Text-only |[@noauthor_open-orcaopenorca_2024] |
|
| 235 |
+
|text_orcamath |0 |200,035 |200,035 |12,691,014 |61,860,987 |Text-only |[@mitra_orca-math_2024] |
|
| 236 |
+
|text_pythoncode25k |0 |49,626 |49,626 |1,629,286 |4,945,892 |Text-only |[@noauthor_flytechpython-codes-25k_2024] |
|
| 237 |
+
|text_pythoncodealpaca |0 |18,612 |18,612 |655,127 |2,683,469 |Text-only |[@noauthor_sahil2801codealpaca-20k_2023] |
|
| 238 |
+
|text_ruozhiba |0 |1,496 |1,496 |69,795 |234,822 |Text-only |[@noauthor_qywuruozhiba_en_nodate] |
|
| 239 |
+
|text_theoremqa |0 |800 |800 |50,065 |3,468 |Text-only |[@chen_theoremqa_2023] |
|
| 240 |
+
|text_wizardlm_evol |0 |69,999 |69,999 |7,753,963 |21,955,856 |Text-only |[@noauthor_wizardlmteamwizardlm_evol_instruct_70k_2024] |
|
| 241 |
+
|text_OpenMathInstruct-2 |0 |1,000,000 |1,000,000 |74,905,850 |413,132,418 |Text-only |[@toshniwal_openmathinstruct-2_2024] |
|
| 242 |
+
|
| 243 |
</Accordion>
|
| 244 |
</Wide>
|
| 245 |
|