Search Results for author:
Found 2 papers, 2 papers with code
Opening the AI black box: program synthesis via mechanistic interpretability
We present MIPS, a novel method for program synthesis based on automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code.
Estimating label quality and errors in semantic segmentation data via any model
We study algorithms to automatically detect such annotation errors, in particular methods to score label quality, such that the images with the lowest scores are least likely to be correctly labeled.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
