Related papers: GPU-accelerated FREDopt package for simultaneous d…
The rapid growth of model scale has necessitated substantial computational resources for fine-tuning. Existing approach such as Low-Rank Adaptation (LoRA) has sought to address the problem of handling the large updated parameters in full…
Currently in HDR brachytherapy planning, a manual fine-tuning of an objective function is necessary to obtain case-specific valid plans. This study intends to facilitate this process by proposing a patient-specific inverse planning…
Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…
Purpose: This paper describes a new method to apply deep-learning algorithms for automatic segmentation of radiosensitive organs from 3D tomographic CT images before computing organ doses using a GPU-based Monte Carlo code. Methods: A deep…
Purpose: The FLASH effect, which reduces the radiosensitivity of healthy tissue while maintaining tumor control at high dose rates, has shown potential for improving radiation therapy. Conformal FLASH proton therapy involves advanced…
Gaussian processes (GPs) are a widely used regression tool, but the cubic complexity of exact solvers limits their scalability. To address this challenge, we extend the GPRat library by incorporating a fully GPU-resident GP prediction…
Optimizing laser and plasma parameters is crucial for enhancing accelerated proton energy in laser-driven proton acceleration with finite laser energy for applications such as cancer therapy. Tight focusing plays a significant role in…
Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as…
Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory costs by updating only a small subset of parameters. Among them,…
Weight-only quantization has emerged as a promising solution to the deployment challenges of large language models (LLMs). However, it necessitates FP-INT operations, which make implementation on general-purpose hardware like GPUs…
Large-scale molecular dynamics simulations with high accuracy have been increasingly popular for their capability to bridge the gap between atomistic modeling and mesoscale phenomena. Both machine learning potentials and enhanced sampling…
Purpose: Monte Carlo methods are considered the gold standard for dosimetric computations in radiotherapy. Their execution time is however still an obstacle to the routine use of Monte Carlo packages in a clinical setting. To address this…
The success of large-scale pre-trained models has established fine-tuning as a standard method for achieving significant improvements in downstream tasks. However, fine-tuning the entire parameter set of a pre-trained model is costly.…
Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks, yet they often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a Parameter-Efficient…
The performance of graph programs depends highly on the algorithm, the size and structure of the input graphs, as well as the features of the underlying hardware. No single set of optimizations or one hardware platform works well across all…
This paper introduces a novel approach to automatic ahead-of-time (AOT) parallelization and optimization of sequential Python programs for execution on distributed heterogeneous platforms. Our approach enables AOT source-to-source…
Motivation: Adverse reactions from drug combinations are increasingly common, making their accurate prediction a crucial challenge in modern medicine. Laboratory-based identification of these reactions is insufficient due to the…
To enhance the efficiency, scalability, and cross-survey applicability of stellar parameter inference in large spectroscopic datasets, we present a modular, parallelized Python framework with automated error estimation, built on the LAMOST…
Accurate 3D dose calculation for Pencil Beam Scanning Proton Therapy (PBSPT) is typically performed with Monte Carlo (MC) engines, but their runtimes limit adaptive workflows and repeated evaluations. Current deep-learning proton dose…
Searching for sources of electromagnetic emission in spectral-line radio astronomy interferometric data is a computationally intensive process. Parallel programming techniques and High Performance Computing hardware may be used to improve…