List your company

Visual Question Answering on TextVQA (test val)

58.2AccuracyPromptCD
37.50442.87748.2553.623Feb 24, 2026Mar 4, 2026Mar 12, 2026Mar 20, 2026Mar 28, 2026Apr 5, 2026Apr 13, 2026

Evaluation results

MethodLinks
PromptCD2026.0258.21.34
VanillaVenue=NeurIPS’23, Location=—, Tokens=576, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0458.2—
SVD-PruneVenue=CVPR’25, Location=Encoder, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0457.24—
PyramidDropVenue=CVPR’25, Location=LLM, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0456.6—
PyramidDropVenue=AAAI’25, Location=LLM, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0456.5—
SVD-PruneVenue=—, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0456.14—
ViCropvariant=grad-att2026.0256.060.89
VisionZipVenue=CVPR’25, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0455.8—
ViCropvariant=rel-att2026.0255.171.16
SVD-PruneVenue=—, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0455.14—
SVD-PruneVenue=—, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0454.81—
SVD-PruneVenue=—, Location=Encoder, Tokens=16, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0454.03—
SparseVLMVenue=ICLR’25, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0453.4—
VisionZipVenue=CVPR’25, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0453.1—
FastVVenue=ECCV’24, Location=LLM, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0452.5—
ToMeVenue=ICLR’23, Location=Encoder, Tokens=192, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0452.1—
ViCropvariant=pure-grad2026.0251.672.36
FastVVenue=ECCV’24, Location=LLM, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0450.6—
PyramidDropVenue=CVPR’25, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0450.6—
TRIMVenue=arXiv’25, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0450—
SAM2026.0249.423.33
ToMeVenue=ICLR’23, Location=Encoder, Tokens=128, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0449.1—
YOLO2026.0248.840.35
CLIP2026.0248.551.07
Original2026.0247.80.17
FastVVenue=ECCV’24, Location=LLM, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0447.8—
SparseVLMVenue=ICML’25, Location=LLM, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0446.1—
ToMeVenue=ICLR’23, Location=Encoder, Tokens=64, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0445.3—
FastVVenue=ECCV’24, Location=LLM, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0442.5—
ToMeVenue=ICLR’23, Location=Encoder, Tokens=32, Base Model=LLaVA-1.5-7B, Retraining Status=without retraining2026.0438.3—