BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

Astro Proposes Outlier-Robust LLM Quantization

Sep 11, 2026

Astro proposed activation-guided structured regularization to reduce accuracy loss from weight and activation outliers during post-training quantization.

Read the original at awesomepapers.ioOpens the publisher's site in a new tab

More in Open-weight & owned stack