Related papers: FermiKit: assembly-based variant calling for Illum…

Reconstructing visual information from brain activity via computer vision technology provides an intuitive understanding of visual neural mechanisms. Despite progress in decoding fMRI data with generative models, achieving accurate…

The Ribbit system is a compact Scheme implementation running on the Ribbit Virtual Machine (RVM) that has been ported to a dozen host languages. It supports a simple Foreign Function Interface (FFI) allowing extensions to the RVM directly…

Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…

We present FIT: a transformer-based architecture with efficient self-attention and adaptive computation. Unlike original transformers, which operate on a single sequence of data tokens, we divide the data tokens into groups, with each group…

Transcriptome assembly from RNA-Seq reads is an active area of bioinformatics research. The ever-declining cost and the increasing depth of RNA-Seq have provided unprecedented opportunities to better identify expressed transcripts. However,…

Sequential recommendation aims to model users' evolving preferences based on their historical interactions. Recent advances leverage Transformer-based architectures to capture global dependencies, but existing methods often suffer from high…

Motivation: Omics data, such as transcriptomics or phosphoproteomics, are broadly used to get a snap-shot of the molecular status of cells. In particular, changes in omics can be used to estimate the activity of pathways, transcription…

Small animal Positron Emission Tomography (PET) is dedicated to small animal imaging, which requires high position and energy precision, as well as good flexibility and efficiency of the electronics. This paper presents the design of a…

Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a…

Processing-in-memory (PIM) seeks to eliminate computation/memory data transfer using devices that support both storage and logic. Stateful logic techniques such as IMPLY, MAGIC and FELIX can perform logic gates within memristive crossbar…

Lengthy documents pose a unique challenge to neural language models due to substantial memory consumption. While existing state-of-the-art (SOTA) models segment long texts into equal-length snippets (e.g., 128 tokens per snippet) or deploy…

Transformer-based models, such as BERT and ViT, have achieved state-of-the-art results across different natural language processing (NLP) and computer vision (CV) tasks. However, these models are extremely memory intensive during their…

Patch reviewing is critical for software development, especially in distributed open-source development, which highly depends on voluntary work, such as Linux. This paper studies the past 10 years of patch reviews of the Linux memory…

We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we…

Reliable identification of fracture origins in alumina matrix composite hip and knee implants is critical for quality assurance and patient safety, yet current fractographic workflows are time-consuming, partly subjective, and reliant on…

Collaborative filtering (CF) is widely adopted in industrial recommender systems (RecSys) for modeling user-item interactions across numerous applications, but often struggles with cold-start and data-sparse scenarios. Recent advancements…

Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dataset. Although several DFQ methods have been proposed for…

The rapid growth of industrial Internet of Things (IIoT) systems has created new challenges for anomaly detection in high-dimensional, multivariate time-series, where privacy, scalability, and communication efficiency are critical.…

LensKit is an open-source toolkit for building, researching, and learning about recommender systems. First released in 2010 as a Java framework, it has supported diverse published research, small-scale production deployments, and education…

As transformer sequence lengths grow, existing pipeline parallelisms incur suboptimal performance due to the quadratic attention computation and the substantial memory overhead. To relieve these challenges, we propose HelixPipe, a novel…