Astra identifies game policies from raw weight matrices and fixes reasoning loops in Qwen3.5-0.8B by editing 0.016% of parameters, lifting MATH-500 scores from 7.9% to 48.1% without training loops.
A PyTorch implementation of Binarized Neural Networks (BNNs) with Shift-based Batch Normalization and AdaMax optimizer. - Wzx0110/PyTorch-BNN-Reimplementation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results