Related papers: A study of convolution models for background corre…

Multivariate analysis of fMRI data has benefited substantially from advances in machine learning. Most recently, a range of probabilistic latent variable models applied to fMRI data have been successful in a variety of tasks, including…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Recently, efficiently deploying deep learning solutions on the edge has received increasing attention. New platforms are emerging to support the increasing demand for flexibility and high performance. In this work, we explore the efficient…

We propose a two-stage estimation method of variance components in time series models known as FDSLRMs, whose observations can be described by a linear mixed model (LMM). We based estimating variances, fundamental quantities in a time…

Linear mixed models (LMMs) are a popular class of methods for analyzing longitudinal and clustered data. However, such models can be sensitive to outliers, and this can lead to biased inference on model parameters and inaccurate prediction…

This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…

We primarily study a special a weighted low-rank approximation of matrices and then apply it to solve the background modeling problem. We propose two algorithms for this purpose: one operates in the batch mode on the entire data and the…

Future gravitational-wave detectors, especially the Laser Interferometer Space Antenna (LISA), will be sensitive to black hole binaries formed in astrophysical environments that promote large eccentricities and spin-induced orbital…

Representational Similarity Analysis (RSA) aims to explore similarities between neural activities of different stimuli. Classical RSA techniques employ the inverse of the covariance matrix to explore a linear model between the neural…

Training LLMs presents significant memory challenges due to growing size of data, weights, and optimizer states. Techniques such as data and model parallelism, gradient checkpointing, and offloading strategies address this issue but are…

We introduce CoLoRA (Convolutional Low-Rank Adaptation), a parameter-efficient fine-tuning method for convolutional neural networks (CNNs). CoLoRA extends LoRA to convolutional layers by decomposing kernel updates into lightweight depthwise…

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants…

Recently, large language models (LLMs) have expanded into various domains. However, there remains a need to evaluate how these models perform when prompted with commonplace queries compared to domain-specific queries, which may be useful…

Meta-learning that uses implicit gradient have provided an exciting alternative to standard techniques which depend on the trajectory of the inner loop training. Implicit meta-learning (IML), however, require computing $2^{nd}$ order…

Estimating the clutter-plus-noise covariance matrix in high-dimensional STAP is challenging in the presence of Internal Clutter Motion (ICM) and a high noise floor. The problem becomes more difficult in low-sample regimes, where the Sample…

This work introduces the Burdened Bayesian Logistic Regression Model (BBLRM), an enhancement of the Bayesian Logistic Regression Model (BLRM) for dose-finding in phase I oncology trials. The BLRM determines the maximum tolerated dose (MTD)…

The rapid development of parameter-efficient fine-tuning methods has noticeably improved the efficiency of adapting large language models. Among these, LoRA has gained widespread popularity due to its strong balance of effectiveness and…

Modern interferometric imaging relies on advanced calibration that incorporates direction-dependent effects. Their increasing number of antennas (e.g. in LOFAR, VLA, MeerKAT/SKA) and sensitivity are often tempered with the accuracy of their…

Adapter-based Federated Large Language Models (FedLLMs) are widely adopted to reduce the computational, storage, and communication overhead of full-parameter fine-tuning for web-scale applications while preserving user privacy. By freezing…

The enhanced Gaussian noise (EGN) model, which accounts for inter-channel stimulated Raman scattering (ISRS), has been extensively utilized for evaluating nonlinear interference (NLI) within the C+L band. Compared to closed-form expressions…