QuaSAR: Quantization Compensation via Stable Activation-Aware Rank Truncation

Excerpt

arXiv:2608.14149v1 Announce Type: new Abstract: Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation. To constrain additional model storage overhead, several existing methods gate layer selection by goodness-of-fit, retaining only those layers whose compensation yields a positive residual fit score and discarding the rest. In this paper, we show that, under the low-bit W4A4 setting, this gating mechanism fails to distinguish poo