foggyforest/Qwen2-VL-2B-ViSA-80K
Image-Text-to-Text
•
Updated
•
4
Datasets:
Dataset Viewer
id
stringlengths 2
214
| conversations
listlengths 2
42
| data_source
stringclasses 54
values |
|---|---|---|
identity_199141 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the date displayed on the image?"
},
{
"from": "gpt",
"value": "The answer is 20120928"
}
] | PMC-VQA(MathV360K) |
cauldron/vqarad/images/vqarad_00000011.png | [
{
"from": "human",
"value": "What plane is seen?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Pa."
},
{
"from": "human",
"value": "Is this an mri?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How can the distribution in this image be described?"
},
{
"from": "gpt",
"value": "Micronodular."
},
{
"from": "human",
"value": "What type of distributions is seen on this image?"
},
{
"from": "gpt",
"value": "Micronodular."
},
{
"from": "human",
"value": "Is there lymphadenopathy?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is lymphadenopathy present?"
},
{
"from": "gpt",
"value": "No."
}
] | vqarad(cauldron,llava_format) |
identity_200258 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the date displayed on the image?"
},
{
"from": "gpt",
"value": "The answer is 20080309"
}
] | PMC-VQA(MathV360K) |
identity_201190 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the coordinate of the labeled region in the image?"
},
{
"from": "gpt",
"value": "The answer is 46/-38/52"
}
] | PMC-VQA(MathV360K) |
identity_252809 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: Which specific protein or gene is associated with the notochord staining indicated by the red arrowheads in the microphotographs?"
},
{
"from": "gpt",
"value": "The answer is Od-IQGAP, Od-leprecan, Od-Zipper"
}
] | PMC-VQA(MathV360K) |
identity_80791 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the measure of the angle that is not labeled in the parallelogram?"
},
{
"from": "gpt",
"value": "The answer is The fourth angle measures (360 - (3y + 1) - (4x - 5) - (3x + 11))°"
}
] | Geometry3K(MathV360K) |
identity_221870 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the maximum velocity measurement displayed on the image?"
},
{
"from": "gpt",
"value": "The answer is 367 cm/s"
}
] | PMC-VQA(MathV360K) |
identity_222957 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the scale range of velocity measurement in this Doppler ultrasound image?"
},
{
"from": "gpt",
"value": "The answer is +1.72 m/s to -0.98 m/s"
}
] | PMC-VQA(MathV360K) |
identity_83867 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the relationship between the angles marked in pink in the given diagram?"
},
{
"from": "gpt",
"value": "The answer is (15x - 8y) = (6x + 14y)"
}
] | Geometry3K(MathV360K) |
identity_193917 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the diameter of the vessel at the location of the red arrows?"
},
{
"from": "gpt",
"value": "The answer is 0.15 mm"
}
] | PMC-VQA(MathV360K) |
identity_109083 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What time is displayed on the image?"
},
{
"from": "gpt",
"value": "The answer is 11:57:58"
}
] | PMC-VQA(MathV360K) |
identity_111397 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the acquisition time of the X-ray image?"
},
{
"from": "gpt",
"value": "The answer is 17:22:49"
}
] | PMC-VQA(MathV360K) |
identity_112358 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What two proteins are labeled in the image?"
},
{
"from": "gpt",
"value": "The answer is NF200kDa and ankyrin-G"
}
] | PMC-VQA(MathV360K) |
identity_202303 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the maximum height indicated on the color scale of the image?"
},
{
"from": "gpt",
"value": "The answer is 13.0 nm"
}
] | PMC-VQA(MathV360K) |
identity_201770 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the time of the study shown in the image?"
},
{
"from": "gpt",
"value": "The answer is 16:55:43"
}
] | PMC-VQA(MathV360K) |
identity_205272 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the date when this ultrasound image was taken?"
},
{
"from": "gpt",
"value": "The answer is 16/03/09"
}
] | PMC-VQA(MathV360K) |
identity_206186 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the length of the object indicated by the arrow in centimeters?"
},
{
"from": "gpt",
"value": "The answer is 16 cm"
}
] | PMC-VQA(MathV360K) |
identity_206631 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What anatomical structures are labeled in the bottom right image?"
},
{
"from": "gpt",
"value": "The answer is interlobular BD, ductules of periportal biliary plexus"
}
] | PMC-VQA(MathV360K) |
identity_80476 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the relationship between x and y?"
},
{
"from": "gpt",
"value": "The answer is 20 - 5x = y and 2x + 6 = 3/5y + 2"
}
] | Geometry3K(MathV360K) |
identity_254172 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What are the MRI coordinates for the center of the left STN, and in which shape are these coordinates displayed?"
},
{
"from": "gpt",
"value": "The answer is R = 1.95, A = 12.10, L = 1.76, V = 331.00"
}
] | PMC-VQA(MathV360K) |
identity_219526 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the intensity value for the pixel at the center of the left STN?"
},
{
"from": "gpt",
"value": "The answer is 313.00"
}
] | PMC-VQA(MathV360K) |
identity_129977 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the angle of the deformity measured on the radiograph?"
},
{
"from": "gpt",
"value": "The answer is 25.5°"
}
] | PMC-VQA(MathV360K) |
identity_129983 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the date on which this CT scan was taken?"
},
{
"from": "gpt",
"value": "The answer is 9/9/2009"
}
] | PMC-VQA(MathV360K) |
identity_131851 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the intensity of the brightest spot on the image according to the color scale?"
},
{
"from": "gpt",
"value": "The answer is 13.14"
}
] | PMC-VQA(MathV360K) |
identity_181944 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What two proteins are indicated in the caption as being visualized in the image?"
},
{
"from": "gpt",
"value": "The answer is Flk1:GFP and Vimentin"
}
] | PMC-VQA(MathV360K) |
identity_258760 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What specific brain region is highlighted in the high-resolution brain images, and what is the correlation coefficient and p-value for the emotional condition?"
},
{
"from": "gpt",
"value": "The answer is Lateral PFC, R = .63, p = .004"
}
] | PMC-VQA(MathV360K) |
identity_118635 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the concentration of the compound used in the experiment?"
},
{
"from": "gpt",
"value": "The answer is 240 nM"
}
] | PMC-VQA(MathV360K) |
cauldron/vqarad/images/vqarad_00000161.png | [
{
"from": "human",
"value": "What is the image plane?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Axial."
},
{
"from": "human",
"value": "Is there an aortic aneurysm?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Can an aortic aneurysm be appreciated?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are adrenal glands present in this image?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Can you see the adrenals?"
},
{
"from": "gpt",
"value": "No."
}
] | vqarad(cauldron,llava_format) |
cauldron/vqarad/images/vqarad_00000164.png | [
{
"from": "human",
"value": "What is abnormal about the image?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "White matter plaques."
},
{
"from": "human",
"value": "Is gray or white matter highlighted in this image?"
},
{
"from": "gpt",
"value": "Gray matter."
},
{
"from": "human",
"value": "Which is highlighted in this image, white or gray matter?"
},
{
"from": "gpt",
"value": "Gray matter."
},
{
"from": "human",
"value": "What side is the lesion located on?"
},
{
"from": "gpt",
"value": "Right."
},
{
"from": "human",
"value": "Where is the lesion?"
},
{
"from": "gpt",
"value": "Right."
},
{
"from": "human",
"value": "Is the lesion located in gray or white matter?"
},
{
"from": "gpt",
"value": "White matter."
},
{
"from": "human",
"value": "Is the lesion seen in the gray or white matter?"
},
{
"from": "gpt",
"value": "White matter."
}
] | vqarad(cauldron,llava_format) |
cauldron/vqarad/images/vqarad_00000166.png | [
{
"from": "human",
"value": "Is the contrast in the bowels or the vasculature?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "In the bowels."
},
{
"from": "human",
"value": "Are any organs besides the intestines present in this image?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Besides the intestines, what other organs are present?"
},
{
"from": "gpt",
"value": "Kidneys."
},
{
"from": "human",
"value": "Is the pathologic part of this image the small bowel or colon?"
},
{
"from": "gpt",
"value": "Small bowel."
},
{
"from": "human",
"value": "Where is the intussesception located?"
},
{
"from": "gpt",
"value": "Small bowel."
}
] | vqarad(cauldron,llava_format) |
cauldron/vqarad/images/vqarad_00000186.png | [
{
"from": "human",
"value": "What does this represent?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Hydropneumothorax."
},
{
"from": "human",
"value": "What kind of image is this?"
},
{
"from": "gpt",
"value": "Chest x ray."
},
{
"from": "human",
"value": "What modality is this?"
},
{
"from": "gpt",
"value": "Chest x ray."
},
{
"from": "human",
"value": "Which side is abnormal?"
},
{
"from": "gpt",
"value": "Left."
},
{
"from": "human",
"value": "Which lung has a defect?"
},
{
"from": "gpt",
"value": "Left."
},
{
"from": "human",
"value": "Do you see fluid in the left lung?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is there fluid in the left lung?"
},
{
"from": "gpt",
"value": "Yes."
}
] | vqarad(cauldron,llava_format) |
identity_196953 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What are the labeled structures in the image?"
},
{
"from": "gpt",
"value": "The answer is f - fornix, dmh - dorsomedial hypothalamus, vmh - ventromedial hypothalamus, arc - arcuate nucleus"
}
] | PMC-VQA(MathV360K) |
identity_198883 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the diameter of the area measured by the Q-Box?"
},
{
"from": "gpt",
"value": "The answer is 5.0 mm"
}
] | PMC-VQA(MathV360K) |
identity_183801 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the name of the tract shown in the image?"
},
{
"from": "gpt",
"value": "The answer is SC-Pulvinar-Amygdala Tract"
}
] | PMC-VQA(MathV360K) |
identity_243815 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: Identify the sequence of steps shown in the images from left to right, and explain the purpose of each step in the context of brain imaging"
},
{
"from": "gpt",
"value": "The answer is Gray Matter Parcellation, Tractography, Thresholded WM Tract, WM Tract Atlas, DW Image, WM Tracts in DW Space"
}
] | PMC-VQA(MathV360K) |
identity_259755 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the size of the cystic structure seen on B-mode US in the right kidney?"
},
{
"from": "gpt",
"value": "The answer is 1.28 cm"
}
] | PMC-VQA(MathV360K) |
identity_260460 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: Identify the specific anatomical structures labeled in the image and explain their significance in the context of a right upper lobectomy"
},
{
"from": "gpt",
"value": "The answer is A1+3 stump, V1-3 stump, A2 stump, B1-3 stump, SVC, Azygos vein"
}
] | PMC-VQA(MathV360K) |
identity_113332 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the numerical value of the dimension indicated in the M-mode long-axis images?"
},
{
"from": "gpt",
"value": "The answer is 3.180"
}
] | PMC-VQA(MathV360K) |
identity_121106 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What type of cells form a thick layer of flattened cells in the epithelial layer?"
},
{
"from": "gpt",
"value": "The answer is AECs"
}
] | PMC-VQA(MathV360K) |
identity_123062 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the time indicated on the image?"
},
{
"from": "gpt",
"value": "The answer is 09:52:41"
}
] | PMC-VQA(MathV360K) |
identity_208659 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the size of the cystic structure indicated by the white arrow?"
},
{
"from": "gpt",
"value": "The answer is 1.28 cm"
}
] | PMC-VQA(MathV360K) |
identity_208873 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the distance from the center of the circle to the point labeled OLRP?"
},
{
"from": "gpt",
"value": "The answer is 2.5 cm"
}
] | PMC-VQA(MathV360K) |
cauldron/vqarad/images/vqarad_00000012.png | [
{
"from": "human",
"value": "How would you describe the mass?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Isointense."
},
{
"from": "human",
"value": "What are the characteristics of the mass?"
},
{
"from": "gpt",
"value": "Isointense."
},
{
"from": "human",
"value": "Is there a fracture of the skull?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the location of the mass?"
},
{
"from": "gpt",
"value": "Left temporal horn."
},
{
"from": "human",
"value": "Where is the mass?"
},
{
"from": "gpt",
"value": "Left temporal horn."
},
{
"from": "human",
"value": "Are there other abnormalities besides the mass in the temporal horn?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Besides the mass in the temporal horn, are there other enhancements in the image?"
},
{
"from": "gpt",
"value": "Yes."
}
] | vqarad(cauldron,llava_format) |
cauldron/vqarad/images/vqarad_00000025.png | [
{
"from": "human",
"value": "The mass is located in what region?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Suprasellar."
},
{
"from": "human",
"value": "Where is the mass located?"
},
{
"from": "gpt",
"value": "Suprasellar."
},
{
"from": "human",
"value": "Does this image use contrast or not?"
},
{
"from": "gpt",
"value": "Contrast."
},
{
"from": "human",
"value": "Does this ct have contrast or no contrast?"
},
{
"from": "gpt",
"value": "Contrast."
},
{
"from": "human",
"value": "What does the enhancing periphery of the mass represent?"
},
{
"from": "gpt",
"value": "Calcification."
},
{
"from": "human",
"value": "What is the outer rim of the mass?"
},
{
"from": "gpt",
"value": "Calcification."
}
] | vqarad(cauldron,llava_format) |
cauldron/vqarad/images/vqarad_00000107.png | [
{
"from": "human",
"value": "What do the masses contain?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Fat."
},
{
"from": "human",
"value": "Did the patient ingest contrast prior to taking this image?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Was contrast used in this image?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What organ contains multiple lesions in the above image?"
},
{
"from": "gpt",
"value": "Kidneys."
},
{
"from": "human",
"value": "Which organ has multiple lesions?"
},
{
"from": "gpt",
"value": "Kidneys."
}
] | vqarad(cauldron,llava_format) |
identity_195541 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the size of the largest foreign object in the X-ray?"
},
{
"from": "gpt",
"value": "The answer is 2.28 cm"
}
] | PMC-VQA(MathV360K) |
identity_196113 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the angle of the C-arm in this image?"
},
{
"from": "gpt",
"value": "The answer is LAO 38 CRAN 0"
}
] | PMC-VQA(MathV360K) |
identity_124915 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the maximum value on the y-axis of the stem graph?"
},
{
"from": "gpt",
"value": "The answer is 24000"
}
] | PMC-VQA(MathV360K) |
identity_125316 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the maximum height depicted in the image?"
},
{
"from": "gpt",
"value": "The answer is 773.6 nm"
}
] | PMC-VQA(MathV360K) |
identity_125317 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the minimum height depicted in the image?"
},
{
"from": "gpt",
"value": "The answer is -819.7 nm"
}
] | PMC-VQA(MathV360K) |
identity_127515 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the length of the structure indicated by the measurement D1?"
},
{
"from": "gpt",
"value": "The answer is 4.65 cm"
}
] | PMC-VQA(MathV360K) |
identity_127516 | [
{
"from": "human",
"value": "Hint: Please answer the question and provide the final answer at the end.\nQuestion: What is the thickness of the structure indicated by the measurement D2?"
},
{
"from": "gpt",
"value": "The answer is 0.70 cm"
}
] | PMC-VQA(MathV360K) |
cauldron/robut_wtq/images/robut_wtq_00014919.png | [
{
"from": "human",
"value": "Who has the fastest recorded finish for the men's bupa great south run, between 1990 and 2013?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Joseph Ebuya (KEN)."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00001823.png | [
{
"from": "human",
"value": "What is the difference of the amount sold between boeing and general dynamics in 2007?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "8960."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00017428.png | [
{
"from": "human",
"value": "Who finished directly after the driver who finished in 1:28.745?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Nelson Philippe."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00027368.png | [
{
"from": "human",
"value": "What was the total number of districts within the state of godara?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "7."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00035372.png | [
{
"from": "human",
"value": "Indicate the number of moments he concluded over 10th rank.\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "3."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00035385.png | [
{
"from": "human",
"value": "Which character is mentioned before the letter 'o' in the term \"unrsgn\"?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "E."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00018372.png | [
{
"from": "human",
"value": "How long is the list of countries that won any medals?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "14."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00023069.png | [
{
"from": "human",
"value": "How many episode are not over 14%?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "8."
}
] | robut_wtq(cauldron,llava_format) |
cauldron/robut_wtq/images/robut_wtq_00019913.png | [
{
"from": "human",
"value": "Which schools are in the same town as bishop leblond?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Benton High School, Lafayette High School."
}
] | robut_wtq(cauldron,llava_format) |
136fd208-217f-4173-b85c-729221b2d59e | [
{
"from": "human",
"value": "What is discussed in Section IV of the document from which the image is taken?"
},
{
"from": "gpt",
"value": "Section IV discusses the \"Optimized RG Improvement and Comparison with the Lattice Data,\" focusing on the refinement of Renormalization Group methods and their evaluation against empirical data from lattice simulations."
}
] | VisualWebInstruct(filtered) |
aa1d3c89-5e1f-413e-9774-20fbeb113a8e | [
{
"from": "human",
"value": "What do the matrices in the image represent in relation to the 8-bus system?"
},
{
"from": "gpt",
"value": "The matrices in the image represent the absolute conditional correlation of a loopy 8-bus system before and after an outage in branches 4-7. Each matrix shows the correlation values between different buses (bus numbers are indicated at the top and left of the matrices). The matrices are divided into four scenarios: pre-outage, post-outage, unknown post-outage estimated using Maximum Likelihood Estimation (MLE), and unknown post-outage estimated using Projected Gradient Descent (PGD)."
}
] | VisualWebInstruct(filtered) |
eeedddc8-152f-4d1a-baa3-3b903c49f79d | [
{
"from": "human",
"value": "What is the purpose of the image provided?"
},
{
"from": "gpt",
"value": "The purpose of the image is to showcase a comparison between different methods of generating stylized images from text descriptions. The image compares the results of the method labeled as \"Ours\" with other methods such as \"Text2image + StyleScene\" and \"SVS → CLIPstyler +LT\" across different artistic styles like cubism, fauvism, black pencil sketches, and pop art. The comparison is made to demonstrate the effectiveness of the novel view stylization by the \"Ours\" model."
}
] | VisualWebInstruct(filtered) |
4db52541-d982-4401-a1a3-d3561c78b371 | [
{
"from": "human",
"value": "What does the equation in Figure 9 suggest about the factors influencing the impact of AI-augmented information operations?"
},
{
"from": "gpt",
"value": "The equation in Figure 9 suggests that the impact of AI-augmented information operations is determined by multiple factors including reach, adaptive quality (influenced by LLM ethical factors), and engagement efficiency, which are all decreased by media noise, resistance, and LLM ethical constraints. Additionally, content diversity and LLM technical advantages play a role in further modifying the impact."
}
] | VisualWebInstruct(filtered) |
402b3023-f028-4ea4-80bf-95c25d268b43 | [
{
"from": "human",
"value": "What is the purpose of the different columns in the image comparing upper body clothes manipulation?"
},
{
"from": "gpt",
"value": "The columns in the image represent different methods or algorithms applied to manipulate the clothing of the depicted figures. The initial input shows the original clothing, and each subsequent column shows the result after applying a specific method, such as \"SD Inpaint,\" \"DiffEdit,\" \"StyleCLIP,\" \"HairCLIP+,\" and the method labeled \"Ours.\" The comparison aims to showcase the effectiveness and differences between these techniques in altering the upper body clothes of the figures."
}
] | VisualWebInstruct(filtered) |
681c5ec0-5a00-43f4-a4b8-690b0af7b039 | [
{
"from": "human",
"value": "What model achieves the highest accuracy according to the left chart in Fig. 14, and what is its value?"
},
{
"from": "gpt",
"value": "The Res+APS model achieves the highest accuracy according to the left chart, with a value of 0.848."
}
] | VisualWebInstruct(filtered) |
70b8f858-f2ee-41ec-b50e-f729b680fb7f | [
{
"from": "human",
"value": "What technique is illustrated in the image to create various artistic styles of 3D scenes?"
},
{
"from": "gpt",
"value": "The image demonstrates the use of a technique called Text2NeRF, which generates 3D scenes in different artistic styles based on textual descriptions. The examples include \"Venezia in oil painting style,\" \"future city in Surrealism style,\" \"a unicorn in a forest, CG style,\" and \"a forest in CG style.\" The variations in styles and content show the flexibility of the Text2NeRF technique in creating diverse visual interpretations from text descriptions."
}
] | VisualWebInstruct(filtered) |
9f116942-5925-49a1-9544-a00012dbc6d8 | [
{
"from": "human",
"value": "What is an example of a keyword search on a knowledge graph for finding a person associated with Y Combinator who also has educational ties to Harvard University and Cornell University?"
},
{
"from": "gpt",
"value": "An example would be a search that yields the answer \"Paul Graham,\" as he is the individual who fits the criteria of owning Y Combinator and having graduated from both Harvard University and Cornell University."
}
] | VisualWebInstruct(filtered) |
37ebac61-7760-4fed-b840-52d5b677a5f7 | [
{
"from": "human",
"value": "What metric shows the highest median value in both training and validation phases according to the boxplots?"
},
{
"from": "gpt",
"value": "The Matthews correlation coefficient (shown in green) exhibits the highest median value in both the training and validation phases."
}
] | VisualWebInstruct(filtered) |
6c6babdb-8a11-40e9-bd00-2a19c8e774de | [
{
"from": "human",
"value": "What does the bar color represent in Figure 5.4 for the \"Reason for termination for Experiment 2\"?"
},
{
"from": "gpt",
"value": "In Figure 5.4, the bar colors represent different termination terms in Experiment 2. The blue bars indicate Term 0, the orange bars signify Term 1, and the yellow bars represent Term 2. Each color corresponds to a specific reason for termination across different models and variations labeled as mixLM and FBLM."
}
] | VisualWebInstruct(filtered) |
36848f6f-ad39-4441-8d12-1976efd015be | [
{
"from": "human",
"value": "What is the theme of the images in the lower part of the provided figure?"
},
{
"from": "gpt",
"value": "The images in the lower part of the figure seem to be showcasing different image generation and inpainting techniques by various models, such as TI (Generation), DreamBooth (Generation), ControlNet (Generation), Stable Diffusion (Inpainting), and an example labeled as \"Ours\" (Generation). These examples illustrate the capabilities of each method in creating or completing images."
}
] | VisualWebInstruct(filtered) |
de541ba6-23e0-4469-b554-d09c72555d0f | [
{
"from": "human",
"value": "What do the different colored circles represent in the graph shown in the image?"
},
{
"from": "gpt",
"value": "In the graph, the different colored circles represent measurements from various studies on the astrophysical neutrino flux normalizations. The blue circle labeled \"HESE,\" the orange circle labeled \"Inelasticity,\" the teal circle labeled \"GlobalFit,\" and the purple circle labeled \"Diffuse\" each signify different methodologies or analyses used to measure the neutrino flux."
}
] | VisualWebInstruct(filtered) |
572e6556-6795-458a-9351-658018414b29 | [
{
"from": "human",
"value": "What is the purpose of the various methods shown in this image and what are they being compared on?"
},
{
"from": "gpt",
"value": "The image depicts a comparison of different medical image segmentation methods applied to ultrasound images. These methods, including U-net, Att U-net, UNETR, U-net++, SegNet, AE U-net, SKU-net, SDFNet, MSDSNet, MBANet, and the approach labeled \"Ours,\" are being evaluated on their ability to accurately predict segmentation masks. The comparison is being made on two different datasets, referred to as Dataset 3 and Dataset 4. The purpose of this comparison is to visualize and assess the performance of each method in terms of their precision in segmenting relevant features from the background in medical imaging, which is critical for diagnosis and treatment planning."
}
] | VisualWebInstruct(filtered) |
55f54e56-1069-484b-b45b-85bc30a226f8 | [
{
"from": "human",
"value": "What does the graph on the right in Figure 12 indicate about the performance of instruction-tuned models compared to the models in the left graph?"
},
{
"from": "gpt",
"value": "The graph on the right in Figure 12 shows the performance of instruction-tuned models (Vicuna, MPT-Instruct, Dolly V2) across the same five metrics used in the left graph (LLaMA, MPT, Pythia). The instruction-tuned models generally cover more area in the radar chart, indicating they perform better according to the SSE (Sensitivity Score Evaluation) scheme used in this study. This suggests that tuning models for specific instructional tasks improves their performance in areas like knowledge, long-range understanding, toxicity, word order, and tokenization."
}
] | VisualWebInstruct(filtered) |
5c675835-7457-424b-aee2-75f1e0196039 | [
{
"from": "human",
"value": "What components are involved in the Unified Runner section of the BasicTS architecture?"
},
{
"from": "gpt",
"value": "The Unified Runner section in the BasicTS architecture handles training, validation, and testing processes. It is responsible for optimizing the model, applying curriculum learning, and clipping gradients to ensure stable training dynamics."
}
] | VisualWebInstruct(filtered) |
c1fd358f-8a68-4fae-b205-94e17b7f6e1b | [
{
"from": "human",
"value": "What tasks are being performed by the AI models in the image, and how do they differ in their responses?"
},
{
"from": "gpt",
"value": "In the image, the AI models mPLUG-DocOwl and Mini-GPT4 are tasked with two different activities. First, they convert rows of a table into JSON format. mPLUG-DocOwl and Mini-GPT4 format the JSON differently, as shown by the slight variation in the structure and the inclusion of game \"time\" details. Second, they identify the name and product offerings of a shop in an image. mPLUG-DocOwl identifies it as \"the Scrub Shop\" selling medical uniforms, whereas Mini-GPT4 simply calls it \"Scrub Shop\" and describes it as selling various types of clothing and accessories. The differences in the responses highlight how each model processes and interprets information, with mPLUG-DocOwl providing more precise and relevant information in this instance."
}
] | VisualWebInstruct(filtered) |
7116097a-ed2c-4a05-b4a7-a135acfa7bbd | [
{
"from": "human",
"value": "What is the purpose of the \"Context of use\" section in the use case card template shown in the image?"
},
{
"from": "gpt",
"value": "The \"Context of use\" section is intended to describe all forms in which the AI system is deployed, including specific geographical, behavioral, or functional settings, and the hardware or service it is intended to run on. This helps in understanding the environment and conditions under which the AI system will operate."
}
] | VisualWebInstruct(filtered) |
cauldron/dvqa/images/dvqa_00099411.png | [
{
"from": "human",
"value": "How many stacks of bars contain at least one element with value smaller than 90?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Six."
},
{
"from": "human",
"value": "Is the value of wise in couple smaller than the value of trial in memory?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the seagreen color represent?"
},
{
"from": "gpt",
"value": "Memory."
},
{
"from": "human",
"value": "What is the value of memory in trust?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "What is the label of the first stack of bars from the bottom?"
},
{
"from": "gpt",
"value": "Pay."
},
{
"from": "human",
"value": "What is the label of the first element from the left in each stack of bars?"
},
{
"from": "gpt",
"value": "Couple."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099416.png | [
{
"from": "human",
"value": "How many items sold less than 9 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Seven."
},
{
"from": "human",
"value": "Which item sold the least units in any shop?"
},
{
"from": "gpt",
"value": "Parlor."
},
{
"from": "human",
"value": "How many units did the worst selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Fund."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Cycle."
},
{
"from": "human",
"value": "How many units of the item fund were sold across all the stores?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Did the item parlor in the store glass sold larger units than the item cycle in the store bent?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the red color represent?"
},
{
"from": "gpt",
"value": "Glass."
},
{
"from": "human",
"value": "How many units of the item window were sold in the store bent?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the sixth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Ease."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Bent."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099417.png | [
{
"from": "human",
"value": "How many items sold less than 3 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which item sold the most units in any shop?"
},
{
"from": "gpt",
"value": "Hung."
},
{
"from": "human",
"value": "How many units did the best selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Bench."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Hung."
},
{
"from": "human",
"value": "How many units of the item tape were sold across all the stores?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "Did the item sorry in the store charge sold smaller units than the item bench in the store shore?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the green color represent?"
},
{
"from": "gpt",
"value": "Charge."
},
{
"from": "human",
"value": "How many units of the item sorry were sold in the store charge?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the left?"
},
{
"from": "gpt",
"value": "Bench."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Charge."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099419.png | [
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Peace."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Stay."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "0."
},
{
"from": "human",
"value": "How many algorithms have accuracies higher than 20?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm tent smaller than peace?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm tent?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom?"
},
{
"from": "gpt",
"value": "Tent."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099421.png | [
{
"from": "human",
"value": "Which bar has the smallest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Scene."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "How many bars have values larger than 60?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Is the value of burden larger than scene?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of burden?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What is the label of the fourth bar from the bottom?"
},
{
"from": "gpt",
"value": "Order."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099423.png | [
{
"from": "human",
"value": "How many objects are preferred by less than 2 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Budget."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Ring."
},
{
"from": "human",
"value": "How many total people preferred the object budget across all the categories?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "Is the object taste in the category trust preferred by more people than the object garden in the category sea?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What category does the orchid color represent?"
},
{
"from": "gpt",
"value": "Sea."
},
{
"from": "human",
"value": "How many people prefer the object speech in the category sea?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the left?"
},
{
"from": "gpt",
"value": "Taste."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Sea."
},
{
"from": "human",
"value": "Does the chart contain any negative values?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099427.png | [
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Bent."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Role."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "90."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "How many bars have values smaller than 90?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Is the value of bird smaller than role?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the value of bird?"
},
{
"from": "gpt",
"value": "70."
},
{
"from": "human",
"value": "What is the label of the first bar from the bottom?"
},
{
"from": "gpt",
"value": "Bird."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099429.png | [
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Sort."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Rule."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "60."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "20."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 70?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm sort smaller than rule?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm sort?"
},
{
"from": "gpt",
"value": "80."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Sort."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099436.png | [
{
"from": "human",
"value": "How many algorithms have accuracy higher than 6 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which algorithm has highest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Cost."
},
{
"from": "human",
"value": "What is the highest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Get."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Cost."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm future for all the datasets?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What dataset does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Staff."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm cost in the dataset prison?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the third stack of bars from the left?"
},
{
"from": "gpt",
"value": "Get."
},
{
"from": "human",
"value": "What is the label of the first element from the bottom in each stack of bars?"
},
{
"from": "gpt",
"value": "Staff."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099443.png | [
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Card."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Radar."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many objects are liked by more than 8 people?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "How many people prefer the objects call or gown?"
},
{
"from": "gpt",
"value": "14."
},
{
"from": "human",
"value": "How many people prefer the object couple?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the sixth bar from the bottom?"
},
{
"from": "gpt",
"value": "Boat."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Does the chart contain stacked bars?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099448.png | [
{
"from": "human",
"value": "How many algorithms have accuracy higher than 8 in at least one dataset?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which algorithm has lowest accuracy for any dataset?"
},
{
"from": "gpt",
"value": "Night."
},
{
"from": "human",
"value": "What is the lowest accuracy reported in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which algorithm has the smallest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Herd."
},
{
"from": "human",
"value": "Which algorithm has the largest accuracy summed across all the datasets?"
},
{
"from": "gpt",
"value": "Design."
},
{
"from": "human",
"value": "What is the sum of accuracies of the algorithm pink for all the datasets?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm herd in the dataset space larger than the accuracy of the algorithm pink in the dataset health?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What dataset does the royalblue color represent?"
},
{
"from": "gpt",
"value": "Space."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm herd in the dataset health?"
},
{
"from": "gpt",
"value": "4."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Tale."
},
{
"from": "human",
"value": "What is the label of the first bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Space."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099454.png | [
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Peace."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Pure."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many bars have values larger than 6?"
},
{
"from": "gpt",
"value": "Three."
},
{
"from": "human",
"value": "What is the sum of the values of pure and wire?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Is the value of peace larger than pure?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the value of hurry?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom?"
},
{
"from": "gpt",
"value": "Screen."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there?"
},
{
"from": "gpt",
"value": "Eight."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099458.png | [
{
"from": "human",
"value": "How many objects are preferred by less than 9 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Four."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Shape."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Hotel."
},
{
"from": "human",
"value": "How many total people preferred the object ride across all the categories?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "Is the object shape in the category dear preferred by more people than the object hotel in the category screen?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the darkorange color represent?"
},
{
"from": "gpt",
"value": "Dear."
},
{
"from": "human",
"value": "How many people prefer the object salary in the category screen?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Salary."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Dear."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Two."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099463.png | [
{
"from": "human",
"value": "How many objects are preferred by less than 3 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Labor."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Boat."
},
{
"from": "human",
"value": "How many total people preferred the object finger across all the categories?"
},
{
"from": "gpt",
"value": "19."
},
{
"from": "human",
"value": "What category does the chocolate color represent?"
},
{
"from": "gpt",
"value": "Target."
},
{
"from": "human",
"value": "How many people prefer the object labor in the category dream?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Finger."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Dream."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Four."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099471.png | [
{
"from": "human",
"value": "Which bar has the largest value?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Stand."
},
{
"from": "human",
"value": "Which bar has the smallest value?"
},
{
"from": "gpt",
"value": "Regard."
},
{
"from": "human",
"value": "What is the value of the largest bar?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the value of the smallest bar?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the difference between the largest and the smallest value in the chart?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "How many bars have values smaller than 8?"
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "What is the sum of the values of regard and stand?"
},
{
"from": "gpt",
"value": "11."
},
{
"from": "human",
"value": "Is the value of stand larger than regard?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the value of stand?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the label of the second bar from the left?"
},
{
"from": "gpt",
"value": "Stand."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099472.png | [
{
"from": "human",
"value": "Which item sold the most units?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Soil."
},
{
"from": "human",
"value": "Which item sold the least units?"
},
{
"from": "gpt",
"value": "Stay."
},
{
"from": "human",
"value": "How many units of the the most sold item were sold?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "How many units of the the least sold item were sold?"
},
{
"from": "gpt",
"value": "1."
},
{
"from": "human",
"value": "How many more of the most sold item were sold compared to the least sold item?"
},
{
"from": "gpt",
"value": "7."
},
{
"from": "human",
"value": "How many items sold more than 8 units?"
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "How many units of items boss and nation were sold?"
},
{
"from": "gpt",
"value": "10."
},
{
"from": "human",
"value": "Did the item nation sold more units than soil?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many units of the item nation were sold?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the third bar from the bottom?"
},
{
"from": "gpt",
"value": "Stay."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099476.png | [
{
"from": "human",
"value": "Which object is the most preferred?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Budget."
},
{
"from": "human",
"value": "Which object is the least preferred?"
},
{
"from": "gpt",
"value": "Rule."
},
{
"from": "human",
"value": "How many people prefer the most preferred object?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "How many people prefer the least preferred object?"
},
{
"from": "gpt",
"value": "3."
},
{
"from": "human",
"value": "What is the difference between most and least preferred object?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many objects are liked by more than 3 people?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "How many people prefer the objects budget or rule?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the object budget preferred by less people than sewage?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "How many people prefer the object budget?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "What is the label of the third bar from the left?"
},
{
"from": "gpt",
"value": "Budget."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099479.png | [
{
"from": "human",
"value": "Which algorithm has the highest accuracy?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Shore."
},
{
"from": "human",
"value": "Which algorithm has the lowest accuracy?"
},
{
"from": "gpt",
"value": "Coffee."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with highest accuracy?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm with lowest accuracy?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "How much more accurate is the most accurate algorithm compared the least accurate algorithm?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many algorithms have accuracies lower than 6?"
},
{
"from": "gpt",
"value": "Two."
},
{
"from": "human",
"value": "What is the sum of the accuracies of the algorithms coffee and rate?"
},
{
"from": "gpt",
"value": "8."
},
{
"from": "human",
"value": "Is the accuracy of the algorithm rate larger than stay?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What is the accuracy of the algorithm coffee?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the first bar from the left?"
},
{
"from": "gpt",
"value": "Shore."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099481.png | [
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value greater than 8?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which group of bars contains the largest valued individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "Gold."
},
{
"from": "human",
"value": "What is the value of the largest individual bar in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Cap."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Gold."
},
{
"from": "human",
"value": "What is the sum of all the values in the target group?"
},
{
"from": "gpt",
"value": "24."
},
{
"from": "human",
"value": "Is the value of cap in sheet smaller than the value of target in bay?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the darkkhaki color represent?"
},
{
"from": "gpt",
"value": "Bay."
},
{
"from": "human",
"value": "What is the value of vein in cap?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "What is the label of the third group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Target."
},
{
"from": "human",
"value": "What is the label of the fifth bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Sheet."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "How many bars are there per group?"
},
{
"from": "gpt",
"value": "Five."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099487.png | [
{
"from": "human",
"value": "How many objects are preferred by less than 9 people in at least one category?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Five."
},
{
"from": "human",
"value": "Which object is the most preferred in any category?"
},
{
"from": "gpt",
"value": "Strain."
},
{
"from": "human",
"value": "How many people like the most preferred object in the whole chart?"
},
{
"from": "gpt",
"value": "9."
},
{
"from": "human",
"value": "Which object is preferred by the least number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Birth."
},
{
"from": "human",
"value": "Which object is preferred by the most number of people summed across all the categories?"
},
{
"from": "gpt",
"value": "Strain."
},
{
"from": "human",
"value": "How many total people preferred the object strain across all the categories?"
},
{
"from": "gpt",
"value": "12."
},
{
"from": "human",
"value": "Is the object strain in the category belt preferred by less people than the object cut in the category lack?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What category does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Lack."
},
{
"from": "human",
"value": "How many people prefer the object shade in the category lack?"
},
{
"from": "gpt",
"value": "5."
},
{
"from": "human",
"value": "What is the label of the fourth group of bars from the left?"
},
{
"from": "gpt",
"value": "Cut."
},
{
"from": "human",
"value": "What is the label of the first bar from the left in each group?"
},
{
"from": "gpt",
"value": "Belt."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099491.png | [
{
"from": "human",
"value": "How many groups of bars contain at least one bar with value smaller than 10?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "Zero."
},
{
"from": "human",
"value": "Which group has the smallest summed value?"
},
{
"from": "gpt",
"value": "Stop."
},
{
"from": "human",
"value": "Which group has the largest summed value?"
},
{
"from": "gpt",
"value": "Memory."
},
{
"from": "human",
"value": "Is the value of stop in card larger than the value of memory in sky?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "Are the values in the chart presented in a percentage scale?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "What element does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Tray."
},
{
"from": "human",
"value": "What is the value of essay in blow?"
},
{
"from": "gpt",
"value": "50."
},
{
"from": "human",
"value": "What is the label of the first group of bars from the bottom?"
},
{
"from": "gpt",
"value": "Blow."
},
{
"from": "human",
"value": "What is the label of the second bar from the bottom in each group?"
},
{
"from": "gpt",
"value": "Essay."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "Yes."
},
{
"from": "human",
"value": "Is each bar a single solid color without patterns?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
cauldron/dvqa/images/dvqa_00099495.png | [
{
"from": "human",
"value": "How many items sold more than 4 units in at least one store?\nAnswer the question using a single word or phrase."
},
{
"from": "gpt",
"value": "One."
},
{
"from": "human",
"value": "Which item sold the most units in any shop?"
},
{
"from": "gpt",
"value": "Family."
},
{
"from": "human",
"value": "Which item sold the least units in any shop?"
},
{
"from": "gpt",
"value": "Column."
},
{
"from": "human",
"value": "How many units did the best selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "How many units did the worst selling item sell in the whole chart?"
},
{
"from": "gpt",
"value": "2."
},
{
"from": "human",
"value": "Which item sold the least number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Column."
},
{
"from": "human",
"value": "Which item sold the most number of units summed across all the stores?"
},
{
"from": "gpt",
"value": "Family."
},
{
"from": "human",
"value": "How many units of the item family were sold across all the stores?"
},
{
"from": "gpt",
"value": "15."
},
{
"from": "human",
"value": "Did the item family in the store ship sold smaller units than the item column in the store fury?"
},
{
"from": "gpt",
"value": "No."
},
{
"from": "human",
"value": "What store does the steelblue color represent?"
},
{
"from": "gpt",
"value": "Loan."
},
{
"from": "human",
"value": "How many units of the item family were sold in the store ship?"
},
{
"from": "gpt",
"value": "6."
},
{
"from": "human",
"value": "What is the label of the second group of bars from the left?"
},
{
"from": "gpt",
"value": "Family."
},
{
"from": "human",
"value": "What is the label of the second bar from the left in each group?"
},
{
"from": "gpt",
"value": "Fury."
},
{
"from": "human",
"value": "Are the bars horizontal?"
},
{
"from": "gpt",
"value": "No."
}
] | dvqa(cauldron,llava_format) |
End of preview. Expand
in Data Studio
This dataset was presented in the paper Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents.
- Downloads last month
- 71
Size of downloaded dataset files:
20.6 MB
Size of the auto-converted Parquet files:
20.6 MB
Number of rows:
86,392
Models trained or fine-tuned on foggyforest/ViSA_LlavaOV_80K