SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
Efficientqat: Efficient quantization-aware training for large language models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.
citing papers explorer
-
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
SplitQ improves low-bit PTQ for VLMs by isolating modality-specific outlier channels via MOCD and applying dual-branch adaptive calibration via ACC, outperforming prior methods on six datasets across W4A8 to W3A2 settings.
-
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models
PermuQuant reduces per-group quantization error in diffusion models by sorting channels with similar activation and weight statistics into the same groups using a calibration-checked permutation.