Related papers: FLARE: Task-agnostic embedding model evaluation th…

The static knowledge representations of large language models (LLMs) inevitably become outdated or incorrect over time. While model-editing techniques offer a promising solution by modifying a model's factual associations, they often…

Normalizing Flows (NFs) learn invertible mappings between the data and a Gaussian distribution. Prior works usually suffer from two limitations. First, they add random noise to training samples or VAE latents as data augmentation,…

Cross-device federated learning is an emerging machine learning (ML) paradigm where a large population of devices collectively train an ML model while the data remains on the devices. This research field has a unique set of practical…

The Highly-Adaptive-Lasso(HAL)-TMLE is an efficient estimator of a pathwise differentiable parameter in a statistical model that at minimal (and possibly only) assumes that the sectional variation norm of the true nuisance parameters are…

Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is expensive. When node attributes contain semantic content, such as paper abstracts, web pages, or product descriptions, large language models…

Fair representation learning (FRL) is a popular class of methods aiming to produce fair classifiers via data preprocessing. Recent regulatory directives stress the need for FRL methods that provide practical certificates, i.e., provable…

Latent feature representation methods play an important role in the dimension reduction and statistical modeling of high-dimensional complex data objects. However, existing approaches to assess the quality of these methods often rely on…

Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely accepted that words with similar semantics should be close to…

Low-dimensional representations, or embeddings, of a graph's nodes facilitate several practical data science and data engineering tasks. As such embeddings rely, explicitly or implicitly, on a similarity measure among nodes, they require…

Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In practice, this often involves using imperfect LLM judges and reward models since ground…

After deployment, machine learning models often experience performance degradation due to shifts in data distribution. It is challenging to assess post-deployment performance accurately when labels are missing or delayed. Existing proxy…

Human Pose Estimation (HPE) is increasingly important for applications like virtual reality and motion analysis, yet current methods struggle with balancing accuracy, computational efficiency, and reliable uncertainty quantification (UQ).…

While model architectures and training strategies have become more generic and flexible with respect to different data modalities over the past years, a persistent limitation lies in the assumption of fixed quantities and arrangements of…

Understanding how data moves, transforms, and persists, known as data flow, is fundamental to reasoning in procedural tasks. Despite their fluency in natural and programming languages, large language models (LLMs), although increasingly…

Spectral clustering is a key research topic in the field of machine learning and data mining. Most of the existing spectral clustering algorithms are built upon Gaussian Laplacian matrices, which are sensitive to parameters. We propose a…

Vision-based fall analysis has advanced rapidly, but a key bottleneck remains: visually similarmotions can correspond to very different physical outcomes because small differences in contactmechanics and protective responses are hard to…

Hierarchical classification problems are commonly seen in practice. However, most existing methods do not fully utilize the hierarchical information among class labels. In this paper, a novel label embedding approach is proposed, which…

The recent widespread adoption of drones for studying marine animals provides opportunities for deriving biological information from aerial imagery. The large scale of imagery data acquired from drones is well suited for machine learning…

Lens flare removal is challenging due to the large spatial extent of flare artifacts and their entanglement with scene structures, while existing methods heavily rely on large-scale paired data. We propose a semi-supervised flare removal…

Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. Heterogeneous hardware, unreliable client devices, and energy constraints often characterize edge computing…