Related papers: Up-To Techniques for Behavioural Metrics via Fibra…

Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions. However, these post-hoc explanations may not always be faithful to classifier predictions, which poses a significant…

We observe that current conversational language models often waver in their judgments when faced with follow-up questions, even if the original judgment was correct. This wavering presents a significant challenge for generating reliable…

Wearables activity trackers are becoming widely adopted to understand individual behavior. Understanding behavior may help in self-regulation such as self-monitoring, goal-setting, self-corrective, etc.; Nevertheless, challenges exist in…

Data augmentation is a technique to generate new training data based on existing data. We evaluate the simple and cost-effective method of concatenating the original data examples to build new training instances. Continued training with…

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and…

The central goal of this thesis is to develop methods to experimentally study topological phases. We do so by applying the powerful toolbox of quantum simulation techniques with cold atoms in optical lattices. To this day, a complete…

Disentangling the explanatory factors in complex data is a promising approach for generalizable and data-efficient representation learning. While a variety of quantitative metrics for learning and evaluating disentangled representations…

In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy,…

This paper presents a generalization of the Wasserstein distance for both persistence diagrams and merge trees [20], [66] that takes advantage of the regions of their topological features in the input domain. Specifically, we redefine the…

We propose a novel Wasserstein method with a distillation mechanism, yielding joint learning of word embeddings and topics. The proposed method is based on the fact that the Euclidean distance between word embeddings may be employed as the…

In top-down multi-level design methodologies, design descriptions at higher levels of abstraction are incrementally refined to the final realizations. Simulation based techniques have traditionally been used to verify that such model…

Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training. This creates a tension: how do watermark-induced shifts…

This paper introduces an adversarial method to stress-test trained metrics to evaluate conversational dialogue systems. The method leverages Reinforcement Learning to find response strategies that elicit optimal scores from the trained…

In recent years, foundational models have revolutionized the fields of language and vision, demonstrating remarkable abilities in understanding and generating complex data; however, similar advances in user behavior modeling have been…

Despite their empirical success, neural networks still have difficulty capturing compositional aspects of natural language. This work proposes a simple data augmentation approach to encourage compositional behavior in neural models for…

In counting experiments, one can set an upper limit on the rate of a Poisson process based on a count of the number of events observed due to the process. In some experiments, one makes several counts of the number of events, using…

Since their inception, encoder-decoder models have successfully been applied to a wide array of problems in computational linguistics. The most recent successes are predominantly due to the use of different variations of attention…

Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that…

Large language models perform text generation through high-dimensional internal dynamics, yet the temporal organisation of these dynamics remains poorly understood. Most interpretability approaches emphasise static representations or causal…

Software behavioral models have proven useful for emulating and testing software systems. Many techniques have been proposed to infer behavioral models of software systems from their interaction traces. The quality of the inferred model is…