COVERCAL selects PTQ calibration samples via weighted set cover over outlier channels, with a stylized clipping model showing missed coverage upper-bounds surrogate loss, yielding gains over random and other baselines on LLaMA and Mistral models.
Preserving LLM capabilities through calibration data curation: From analysis to optimization
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
Coverage-Based Calibration for Post-Training Quantization via Weighted Set Cover over Outlier Channels
COVERCAL selects PTQ calibration samples via weighted set cover over outlier channels, with a stylized clipping model showing missed coverage upper-bounds surrogate loss, yielding gains over random and other baselines on LLaMA and Mistral models.
- Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization