Related papers: Towards Refactoring DMARF and GIPSY OSS
Modular programming is a development paradigm that emphasizes self-contained, flexible, and independent pieces of functionality. This practice allows new features to be seamlessly added when desired, and unwanted features to be removed,…
Accurate channel state information (CSI) is essential for downlink precoding in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems with orthogonal frequency-division multiplexing (OFDM). However,…
A structured version of derivative-free random pattern search optimization algorithms is introduced which is able to exploit coordinate partially separable structure (typically associated with sparsity) often present in unconstrained and…
Scientific workflows bridge scientific challenges with computational resources. While dispel4py, a stream-based workflow system, offers mappings to parallel enactment engines like MPI or Multiprocessing, its optimization primarily focuses…
The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by…
This work considers merging two independent models, TTS and A2F, into a unified model to enable internal feature transfer, thereby improving the consistency between audio and facial expressions generated from text. We also discuss the…
In real-world applications, it is challenging to build a speaker verification system that is simultaneously robust against common threats, including spoofing attacks, channel mismatch, and domain mismatch. Traditional automatic speaker…
Mobile and embedded devices are increasingly using microphones and audio-based computational models to infer user context. A major challenge in building systems that combine audio models with commodity microphones is to guarantee their…
Multi-subject fMRI studies are challenging due to the high variability of both brain anatomy and functional brain topographies across participants. An effective way of aggregating multi-subject fMRI data is to extract a shared…
The problems caused by the gap between system- and software-level architecting practices, especially in the context of Systems of Systems where the two disciplines inexorably meet, is a well known issue with a disappointingly low amount of…
Integrated sensing and communication (ISAC) has garnered substantial research interest owing to its pivotal role in advancing the development of next-generation (6G) wireless networks. However, achieving a performance balance between…
As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility for diverse AI workloads, they often fall short in…
The Class Incremental Semantic Segmentation (CISS) extends the traditional segmentation task by incrementally learning newly added classes. Previous work has introduced generative replay, which involves replaying old class samples generated…
With the rapid development of deep learning, the implementation of intricate algorithms and substantial data processing have become standard elements of deep learning projects. As a result, the code has become progressively complex as the…
AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, images, and video, AI-based systems are increasing their complexity. Compared to traditional AI-based…
With the rapid growth in the volume of data sets, models, and devices in the domain of deep learning, there is increasing attention on large-scale distributed deep learning. In contrast to traditional distributed deep learning, the…
To ensure resilient neural network processing on even unreliable hardware, comprehensive reliability analysis against various hardware faults is generally required before the deep neural network models are deployed, and efficient error…
Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives,…
We consider optimization algorithms that are open systems, that is, with external inputs and outputs. Such algorithms arise for instance, when analyzing the effect of noise or disturbance on an algorithm, or when an algorithm is part of…
AI development is embracing open-source paradigm, but the fundamental distinction between AI models and traditional software artifacts may lead to a divergent open-source development paradigm with different collaborative practices, which…