26 citations · 53 across the 7 of their papers we have counts for
7 papers
STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization
Marco Federici, Riccardo Del Chiaro, Boris van Breugel +2
Quantization is the key method for reducing inference latency, power and memory footprint of generative AI models. However, accuracy often degrades sharply when activations are qua…
HadaNorm: Diffusion Transformer Quantization through Mean-Centered Transformations
Marco Federici, Riccardo Del Chiaro, Boris van Breugel +2
Diffusion models represent the cutting edge in image generation, but their high memory and computational demands hinder deployment on resource-constrained devices. Post-Training Qu…
Position: All Current Generative Fidelity and Diversity Metrics are Flawed
Ossi Räisä, Boris van Breugel, Mihaela van der Schaar
Any method's development and practical application is limited by our ability to measure its reliability. The popularity of generative modeling emphasizes the importance of good syn…
RadEdit: stress-testing biomedical vision models via diffusion image editing
Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez +11
Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing. Thi…
Practical Approaches for Fair Learning with Multitype and Multivariate Sensitive Attributes
Tennison Liu, Alex J. Chan, Boris van Breugel +1
It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences. Fair ML has largely focused…
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Boris van Breugel, Trent Kyono, Jeroen Berrevoets +1
Machine learning models have been criticized for reflecting unfair biases in the training data. Instead of solving for this by introducing fair learning algorithms directly, we foc…
Stereotype and Skew: Quantifying Gender Bias in Pre-trained and Fine-tuned Language Models
Daniel de Vassimon Manela, David Errington, Thomas Fisher +2
This paper proposes two intuitive metrics, skew and stereotype, that quantify and analyse the gender bias present in contextual language models when tackling the WinoBias pronoun r…