Related papers: Exploring Contur beyond its default mode: a case s…

Learning to Rank (LTR) from user interactions is challenging as user feedback often contains high levels of bias and noise. At the moment, two methodologies for dealing with bias prevail in the field of LTR: counterfactual methods that…

Despite the existence of numerous colorization methods, several limitations still exist, such as lack of user interaction, inflexibility in local colorization, unnatural color rendering, insufficient color variation, and color overflow. To…

Recent work suggests that changing Convolutional Neural Network (CNN) architecture by introducing a bottleneck in the second layer can yield changes in learned function. To understand this relationship fully requires a way of quantitatively…

Measurements at particle collider experiments, even if primarily aimed at understanding Standard Model processes, can have a high degree of model independence, and implicitly contain information about potential contributions from physics…

Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant…

Prompt learning has become one of the most efficient paradigms for adapting large pre-trained vision-language models to downstream tasks. Current state-of-the-art methods, like CoOp and ProDA, tend to adopt soft prompts to learn an…

Coloring is a notoriously hard problem, and even more so in the online setting, where each arriving vertex has to be colored immediately and irrevocably. Already on trees, which are trivially two-colorable, it is impossible to achieve…

In this work, we investigate \textit{texture learning}: the identification of textures learned by object classification models, and the extent to which they rely on these textures. We build texture-object associations that uncover new…

By allowing models to predict without task-specific training, in-context learning (ICL) with pretrained LLMs has enormous potential in NLP. However, a number of problems persist in ICL. In particular, its performance is sensitive to the…

I present a model of topcolor-assisted technicolor that can have topcolor breaking of the desired pattern, hard masses for all quarks and leptons, mixing among the heavy and light generations, and explicit breaking of all technifermion…

We analyze a model of dynamically broken topcolor in the limit in which the number of colors is large. We show that the second order nature of the phase transition, necessary for the success of topcolor models, passes the nontrivial check…

Understanding the severity of conditions shown in images in medical diagnosis is crucial, serving as a key guide for clinical assessment, treatment, as well as evaluating longitudinal progression. This paper proposes Con- PrO: a novel…

This research project studies the impact of convolutional neural networks (CNN) in image classification tasks. We explore different architectures and training configurations with the use of ReLUs, Nesterov's accelerated gradient, dropout…

Recent research has demonstrated that Large Language Models (LLMs) are not limited to text-only tasks but can also function as multimodal models across various modalities, including audio, images, and videos. In particular, research on 3D…

We address the challenging problem of Natural Language Comprehension beyond plain-text documents by introducing the TILT neural network architecture which simultaneously learns layout information, visual features, and textual semantics.…

With the increasing ability of large language models (LLMs), in-context learning (ICL) has evolved as a new paradigm for natural language processing (NLP), where instead of fine-tuning the parameters of an LLM specific to a downstream task…

We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in…

Methods from computational topology are becoming more and more popular in computer vision and have shown to improve the state-of-the-art in several tasks. In this paper, we investigate the applicability of topological descriptors in the…

In this project, we want to explore the newly emerging field of prompt engineering and apply it to the downstream task of detecting LM biases. More concretely, we explore how to design prompts that can indicate 4 different types of biases:…

We present observations and discussion of previously unreported phenomena discovered while training residual networks. The goal of this work is to better understand the nature of neural networks through the examination of these new…