QAPruner introduces a hybrid sensitivity metric that combines group-wise quantization error simulation and outlier intensity with semantic scores to prune visual tokens, yielding 2.24% higher accuracy than naive baselines at 12.5% token retention on LLaVA models while surpassing dense low-bit models
In: ICCV (2023)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.
citing papers explorer
-
QAPruner: Quantization-Aware Vision Token Pruning for Multimodal Large Language Models
QAPruner introduces a hybrid sensitivity metric that combines group-wise quantization error simulation and outlier intensity with semantic scores to prune visual tokens, yielding 2.24% higher accuracy than naive baselines at 12.5% token retention on LLaVA models while surpassing dense low-bit models
-
DARK: Diagonal-Anchored Repulsive Knowledge Distillation for Vision-Language Models under Extreme Compression
DARK distillation lets a 75M-parameter student model match or exceed a 427M-parameter teacher on fetal ultrasound benchmarks by transitioning from imitating to repelling non-target similarities.