Andrzej Banburski

2 accepted papers

2024

Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling

Weijia Xu, Andrzej Banburski, Nebojsa Jojic

ICML 2024poster

We introduce Reprompting, an iterative sampling algorithm that automatically learns the Chain-of-Thought (CoT) recipes for a given task without human intervention. Through Gibbs sampling, Reprompting infers the CoT recipes that work consistently well for a set of training samples by iteratively samp…

Cited by 29 Source ↗PDF ↗Scholar ↗

2020

Biologically Inspired Mechanisms for Adversarial Robustness

Manish Reddy Vuyyuru, Andrzej Banburski, Nishka Pant, Tomaso Poggio

NeurIPS 2020poster

A convolutional neural network strongly robust to adversarial perturbations at reasonable computational and performance cost has not yet been demonstrated. The primate visual ventral stream seems to be robust to small perturbations in visual stimuli but the underlying mechanisms that give rise to th…

Cited by 36 Source ↗PDF ↗Scholar ↗