BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

LoPRo Improves Low-Rank LLM Quantization

Sep 11, 2026

LoPRo proposed permuted block-wise rotations to improve low-rank quantization of large language models.

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

More in Open-weight & owned stack