Related papers: FitED: A User-Centric, Extensible Software Environ…
Most anomaly detection systems output scores rather than calibrated decisions, leaving practitioners to choose thresholds heuristically and without clear statistical interpretation. Conformal anomaly detection addresses this limitation by…
Time series forecasting is critical for many applications, where deep learning-based point prediction models have demonstrated strong performance. However, in practical scenarios, there is also a need to quantify predictive uncertainty…
Motivation: Alignment-free distance and similarity functions (AF functions, for short) are a well established alternative to two and multiple sequence alignments for many genomic, metagenomic and epigenomic tasks. Due to data-intensive…
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast…
Methods: We have developed a software suite (DataSet Tracker) for real-time analysis designed to run on computers, smartphones, and smart glasses hardware and suitable for resource-constrained, on-the-fly computing in microscopes without…
This article presents a high-throughput computer program, called EasyDD, for batch processing, analyzing and visualizing of spectral data; particularly those related to the new generation of synchrotron detectors and X-ray powder…
Motivated by various data science applications including de-anonymizing user identities in social networks, we consider the graph alignment problem, where the goal is to identify the vertex/user correspondence between two correlated graphs.…
We present PAODING, a toolkit to debloat pretrained neural network models through the lens of data-free pruning. To preserve the model fidelity, PAODING adopts an iterative process, which dynamically measures the effect of deleting a neuron…
Diffusion models have recently enabled precise and photorealistic facial editing across a wide range of semantic attributes. Beyond single-step modifications, a growing class of applications now demands the ability to analyze and track…
We present a scheme to automatically set the precision of floating point variables in an application. We design a framework that profiles applications to measure undesirable numerical behavior at the floating point operation level. We use…
Sequential algorithms are popular for experimental design, enabling emulation, optimisation and inference to be efficiently performed. For most of these applications bespoke software has been developed, but the approach is general and many…
Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph,…
We present a convenient, all-in-one framework for the scientific analysis of fully reduced, (integral-field) spectroscopic data. The GIST pipeline (Galaxy IFU Spectroscopy Tool) is entirely written in Python3 and conducts all steps from the…
PaPy, which stands for parallel pipelines in Python, is a highly flexible framework that enables the construction of robust, scalable workflows for either generating or processing voluminous datasets. A workflow is created from user-written…
We present gradiend, an open-source Python package that operationalizes the GRADIEND method for learning feature directions from factual-counterfactual MLM and CLM gradients in language models. The package provides a unified workflow for…
We introduce DiffFit, a differentiable algorithm for fitting protein atomistic structures into an experimental reconstructed Cryo-Electron Microscopy (cryo-EM) volume map. In structural biology, this process is necessary to…
Fine-tuning large pre-trained foundation models often yields excellent downstream performance but is prohibitively expensive when updating all parameters. Parameter-efficient fine-tuning (PEFT) methods such as LoRA alleviate this by…
Image guided depth completion is the task of generating a dense depth map from a sparse depth map and a high quality image. In this task, how to fuse the color and depth modalities plays an important role in achieving good performance. This…
Asymmetric lineshapes are experimentally observed in Raman spectra of different classes of condensed matter. Determination of the peak parameters, typically done with symmetric pseudo-Voigt functions, in such situations yields unreliable…
Dynamic program analysis (also known as profiling) is well-known for its powerful capabilities of identifying performance inefficiencies in software packages. Although a large number of dynamic program analysis techniques are developed in…