Related papers: PRISM: A Rich Class of Parameterized Submodular In…

Feature subset selection, as a special case of the general subset selection problem, has been the topic of a considerable number of studies due to the growing importance of data-mining applications. In the feature subset selection problem…

Understanding how anatomical shapes evolve in response to developmental covariates and quantifying their spatially varying uncertainties is critical in healthcare research. Existing approaches typically rely on global time-warping…

The sheer scale of modern datasets has resulted in a dire need for summarization techniques that identify representative elements in a dataset. Fortunately, the vast majority of data summarization tasks satisfy an intuitive diminishing…

Dynamic text-attributed graphs (DyTAGs) provide a powerful framework for modeling evolving systems in which node semantics and time-dependent interactions are tightly coupled. Recently, multimodal learning has emerged as a promising yet…

Prompts are the interface for eliciting the capabilities of large language models (LLMs). Understanding their structure and components is critical for analyzing LLM behavior and optimizing performance. However, the field lacks a…

Image coding for machines (ICM) aims to compress images to support downstream AI analysis instead of human perception. For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support…

Long Short-Term Memory (LSTM) neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem…

Recent advances in conditional image generation from diffusion models have shown great potential in achieving impressive image quality while preserving the constraints introduced by the user. In particular, ControlNet enables precise…

E-commerce search systems rely on modeling user behavior to estimate item relevance and user preference, which are typically assumed to be stable and independently learnable signals. However, in practice, user interactions are jointly…

Determining the most appropriate features for machine learning predictive models is challenging regarding performance and feature acquisition costs. In particular, global feature choice is limited given that some features will only benefit…

Highly overparametrized neural networks can display curiously strong generalization performance - a phenomenon that has recently garnered a wealth of theoretical and empirical research in order to better understand it. In contrast to most…

This paper addresses the problem of sequential submodular maximization: selecting and ranking items in a sequence to optimize some composite submodular function. In contrast to most of the previous works, which assume access to the utility…

While data are the primary fuel for machine learning models, they often suffer from missing values, especially when collected in real-world scenarios. However, many off-the-shelf machine learning models, including artificial neural network…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior.…

Matrix functions such as square root, inverse roots, and orthogonalization play a central role in preconditioned gradient methods for neural network training. This has motivated the development of iterative algorithms that avoid explicit…

Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with…

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

Imitation learning is widely used for learning to act in complex environments. While pure neural-based methods handle high dimensional data effectively, they suffer from the requirement of large number of samples and are prone to…