Related papers: CleanSurvival: Automated data preprocessing for ti…

In data-rich domains such as vision, language, and speech, deep learning prevails to deliver high-performance task-specific models and can even learn general task-agnostic representations for efficient finetuning to downstream tasks.…

Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code representations shift. While continual learning…

The automated machine learning (AutoML) process can require searching through complex configuration spaces of not only machine learning (ML) components and their hyperparameters but also ways of composing them together, i.e. forming ML…

This thesis addresses challenges related to data and parameter efficiency in neural language models, with a focus on representation analysis and the introduction of new optimization techniques. The first part examines the properties and…

Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…

Prescriptive process monitoring methods seek to optimize the performance of business processes by triggering interventions at runtime, thereby increasing the probability of positive case outcomes. These interventions are triggered according…

Data preprocessing is a crucial step in the machine learning process that transforms raw data into a more usable format for downstream ML models. However, it can be costly and time-consuming, often requiring the expertise of domain experts.…

Over the past decades, the increase in both frequency and intensity of large-scale wildfires due to climate change has emerged as a significant natural threat. The pressing need to design resilient landscapes capable of withstanding such…

Scientists often use observational time series data to study complex natural processes, but regression analyses often assume simplistic dynamics. Recent advances in deep learning have yielded startling improvements to the performance of…

Experience replay \citep{lin1993reinforcement, mnih2015human} is a widely used technique to achieve efficient use of data and improved performance in RL algorithms. In experience replay, past transitions are stored in a memory buffer and…

Foundational Vision-Language Models (VLMs) excel across diverse tasks, but adapting them to new domains without forgetting prior knowledge remains a critical challenge. Continual Learning (CL) addresses this challenge by enabling models to…

In the absence of data from a randomized trial, researchers often aim to use observational data to draw causal inference about the effect of a treatment on a time-to-event outcome. In this context, interest often focuses on the…

In recent years, deep learning models have become the standard for agricultural computer vision. Such models are typically fine-tuned to agricultural tasks using model weights that were originally fit to more general, non-agricultural…

Modern deep architectures often rely on large-scale datasets, but training on these datasets incurs high computational and storage overhead. Real-world datasets often contain substantial redundancies, prompting the need for more…

In medicine, survival analysis studies the time duration to events of interest such as mortality. One major challenge is how to deal with multiple competing events (e.g., multiple disease diagnoses). In this work, we propose a…

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Common approaches to control a data-center cooling system rely on approximated system/environment models that are built upon the knowledge of mechanical cooling and electrical and thermal management. These models are difficult to design and…

Transductive learning is a supervised machine learning task in which, unlike in traditional inductive learning, the unlabelled data that require labelling are a finite set and are available at training time. Similarly to inductive learning…

As modern data pipelines continue to collect, produce, and store a variety of data formats, extracting and combining value from traditional and context-rich sources such as strings, text, video, audio, and logs becomes a manual process…

Large-scale LP problems from industry usually contain much redundancy that severely hurts the efficiency and reliability of solving LPs, making presolve (i.e., the problem simplification module) one of the most critical components in modern…