14 citations · 24 across the 8 of their papers we have counts for
9 papers
Bits of Grass: Does GPT already know how to write like Whitman?
Piotr Sawicki, Marek Grzes, Fabricio Goes +3
This study examines the ability of GPT-3.5, GPT-3.5-turbo (ChatGPT) and GPT-4 models to generate poems in the style of specific authors using zero-shot and many-shot prompts (which…
How good are variational autoencoders at transfer learning?
Lisa Bonheme, Marek Grzes
Variational autoencoders (VAEs) are used for transfer learning across various research domains such as music generation or medical image analysis. However, there is no principled w…
Crowd Score: A Method for the Evaluation of Jokes using Large Language Model AI Voters as Judges
Fabricio Goes, Zisen Zhou, Piotr Sawicki +2
This paper presents the Crowd Score, a novel method to assess the funniness of jokes using large language models (LLMs) as AI judges. Our method relies on inducing different person…
FONDUE: an algorithm to find the optimal dimensionality of the latent representations of variational autoencoders
Lisa Bonheme, Marek Grzes
When training a variational autoencoder (VAE) on a given dataset, determining the optimal number of latent variables is mostly done by grid search: a costly process in terms of com…
How do Variational Autoencoders Learn? Insights from Representational Similarity
Lisa Bonheme, Marek Grzes
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications. However, their behaviour is not yet fully und…
Be More Active! Understanding the Differences between Mean and Sampled Representations of Variational Autoencoders
Lisa Bonheme, Marek Grzes
The ability of Variational Autoencoders to learn disentangled representations has made them appealing for practical applications. However, their mean representations, which are gen…
Reinforcement Learning using Augmented Neural Networks
Jack Shannon, Marek Grzes
Neural networks allow Q-learning reinforcement learning agents such as deep Q-networks (DQN) to approximate complex mappings from state spaces to value functions. However, this als…
Improving Language Modelling with Noise-contrastive estimation
Farhana Ferdousi Liza, Marek Grzes
Neural language models do not scale well when the vocabulary is large. Noise-contrastive estimation (NCE) is a sampling-based method that allows for fast learning with large vocabu…
Relational Approach to Knowledge Engineering for POMDP-based Assistance Systems as a Translation of a Psychological Model
Marek Grzes, Jesse Hoey, Shehroz Khan +4
Assistive systems for persons with cognitive disabilities (e.g. dementia) are difficult to build due to the wide range of different approaches people can take to accomplishing the…