GridSFM | Small Foundation Models for the Power Grid
GridSFM is an open-source framework for neural surrogate modeling of AC Optimal Power Flow (AC-OPF) on realistic approximations of the US power grids, derived exclusively from open data.
Catalyst Lab
Tools
Loading…
SABER: Scaling-Aware Best-of-N Estimation of Risk
Scaling-Aware Best-of-N Estimation of Risk A Python package for predicting large-scale adversarial risk in Large Language Models under Best-of-N sampling. Paper: https://arxiv.org/pdf/2601.22636 (opens in new tab) Standard LLM safety evaluations use single-shot (ASR@1) metrics, but real attackers can exploit…