Related papers: Conditional Autoregressors are Interpretable Class…

Numerous applications of machine learning involve representing probability distributions over high-dimensional data. We propose autoregressive quantile flows, a flexible class of normalizing flow models trained using a novel objective based…

Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where…

Approximate learning machines have become popular in the era of small devices, including quantised, factorised, hashed, or otherwise compressed predictors, and the quest to explain and guarantee good generalisation abilities for such…

Explainable artificial intelligence is the attempt to elucidate the workings of systems too complex to be directly accessible to human cognition through suitable side-information referred to as "explanations". We present a trainable…

Rapid learning requires flexible representations to quickly adopt to new evidence. We develop a novel class of models called Attentive Recurrent Comparators (ARCs) that form representations of objects by cycling through them and making…

Learning policies that effectively utilize language instructions in complex, multi-task environments is an important problem in sequential decision-making. While it is possible to condition on the entire language instruction directly, such…

Existing integer-valued autoregressive (INAR) models for count random fields suffer from difficulties in characterizing the stationary marginal distribution and in computing conditional probabilities (as required for likelihood inference).…

How to interpret a data mining model has received much attention recently, because people may distrust a black-box predictive model if they do not understand how the model works. Hence, it will be trustworthy if a model can provide…

Autoregressive (AR) image generation has recently emerged as a powerful paradigm for image synthesis. Leveraging the generation principle of large language models, they allow for efficiently generating deceptively real-looking images,…

Interpretability is highly desired for deep neural network-based classifiers, especially when addressing high-stake decisions in medical imaging. Commonly used post-hoc interpretability methods have the limitation that they can produce…

Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability. Inspired by their notable success in NLP field, autoregressive models have been…

The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing…

Autoregressive (AR) models excel at generating temporally coherent audio by producing tokens sequentially, yet they often falter in faithfully following complex textual prompts, especially those describing complex sound events. We uncover a…

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

When deploying machine learning solutions, they must satisfy multiple requirements beyond accuracy, such as fairness, robustness, or safety. These requirements are imposed during training either implicitly, using penalties, or explicitly,…

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

Recently, self-supervised instance discrimination methods have achieved significant success in learning visual representations from unlabeled photographic images. However, given the marked differences between photographic and medical…

Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based interpretations remain ill-understood in the context of…

In-context learning (ICL) has transformed the use of large language models (LLMs) for NLP tasks, enabling few-shot learning by conditioning on labeled examples without finetuning. Despite its effectiveness, ICL is prone to errors,…

Goal-conditioned planning benefits from learned low-dimensional representations of rich observations. While compact latent representations typically learned from variational autoencoders or inverse dynamics enable goal-conditioned decision…