Author

M. P. Bento

h-index 1 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries

GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers and requires no specific calibration data, no quantization simulation, and adds negligible training overhead.

M. P. Bento, João Seabra · arXiv.org · 1 citation