Related papers: Functional Specification of the RAVENS Neuroproces…

Retrieval-Augmented Generation (RAG) relies on large-scale Approximate Nearest Neighbor Search (ANNS) to retrieve semantically relevant context for large language models. Among ANNS methods, IVF-PQ offers an attractive balance between…

With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CAVs are computed by…

NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank Imaging…

Resistive Random-Access Memory (RRAM) is well-suited to accelerate neural network (NN) workloads as RRAM-based Processing-in-Memory (PIM) architectures natively support highly-parallel multiply-accumulate (MAC) operations that form the…

The Relevance Vector Machine (RVM) is a recently developed machine learning framework capable of building simple models from large sets of candidate features. Here, we describe a protocol for using the RVM to explore very large numbers of…

The vertex-centric programming model is an established computational paradigm recently incorporated into distributed processing frameworks to address challenges in large-scale graph processing. Billion-node graphs that exceed the memory…

Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception. However, most existing…

Many FPGAs vendors have recently included embedded processors in their devices, like Xilinx with ARM-Cortex A cores, together with programmable logic cells. These devices are known as Programmable System on Chip (PSoC). Their ARM cores…

This paper presents a novel framework for designing support vector machines (SVMs), which does not impose restriction on the SVM kernel to be positive-definite and allows the user to define memory constraint in terms of fixed template…

Referring Audio-Visual Segmentation (Ref-AVS) aims to segment target objects in audible videos based on given reference expressions. Prior works typically rely on learning latent embeddings via multimodal fusion to prompt a tunable SAM/SAM2…

A novel machine learning algorithm is presented, serving as a data-driven turbulence modeling tool for Reynolds Averaged Navier-Stokes (RANS) simulations. This machine learning algorithm, called the Tensor Basis Random Forest (TBRF), is…

Multi-task visual grounding (MTVG) includes two sub-tasks, i.e., Referring Expression Comprehension (REC) and Referring Expression Segmentation (RES). The existing representative approaches generally follow the research pipeline which…

In the biological nervous system, large neuronal populations work collaboratively to encode sensory stimuli. These neuronal populations are characterised by a diverse distribution of tuning curves, ensuring that the entire range of input…

Recurrent Neural Network (RNN) applications form a major class of AI-powered, low-latency data center workloads. Most execution models for RNN acceleration break computation graphs into BLAS kernels, which lead to significant inter-kernel…

It is being proved that the neurochip \Totem{} is a viable solution for high quality and real time computational tasks in HEP, including event classification, triggering and signal processing. The architecture of the chip is based on a…

Edge vision systems combining sensing and embedded processing promise low-latency, decentralized, and energy-efficient solutions that forgo reliance on the cloud. As opposed to conventional frame-based vision sensors, event-based cameras…

Transformer neural networks (TNN) have been widely utilized on a diverse range of applications, including natural language processing (NLP), machine translation, and computer vision (CV). Their widespread adoption has been primarily driven…

Recently, the field of deep learning has received great attention by the scientific community and it is used to provide improved solutions to many computer vision problems. Convolutional neural networks (CNNs) have been successfully used to…

Tensor Network (TN) Kernel Machines speed up model learning by representing parameters as low-rank TNs, reducing computation and memory use. However, most TN-based Kernel methods are deterministic and ignore parameter uncertainty. Further,…

Low-power sensing technologies, such as wearables, have emerged in the healthcare domain since they enable continuous and non-invasive monitoring of physiological signals. In order to endow such devices with clinical value, classical signal…