Related papers: AAC: Admissible-by-Architecture Differentiable Lan…

Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requires predictable latency and stable behavior under limited CPU parallelism. Accuracy-only…

Deep neural networks are widely deployed in many fields. Due to the in-situ computation (known as processing in memory) capacity of the Resistive Random Access Memory (ReRAM) crossbar, ReRAM-based accelerator shows potential in accelerating…

Neural Image Compression (NIC) has revolutionized image compression with its superior rate-distortion performance and multi-task capabilities, supporting both human visual perception and machine vision tasks. However, its widespread…

Traffic light and sign detectors on autonomous cars are integral for road scene perception. The literature is abundant with deep learning networks that detect either lights or signs, not both, which makes them unsuitable for real-life…

Adversarially robust PAC learning has proved to be challenging, with the currently best known learners [Montasser et al., 2021a] relying on improper methods based on intricate compression schemes, resulting in sample complexity exponential…

Advanced Persistent Threats (APTs) pose a major cybersecurity challenge due to their stealth and ability to mimic normal system behavior, making detection particularly difficult in highly imbalanced datasets. Traditional anomaly detection…

Semantic segmentation has made much progress with increasingly powerful pixel-wise classifiers and incorporating structural priors via Conditional Random Fields (CRF) or Generative Adversarial Networks (GAN). We propose a simpler…

We introduce a differentiable random access memory module with $O(1)$ performance regardless of size, scaling to billions of entries. The design stores entries on points of a chosen lattice to calculate nearest neighbours of arbitrary…

Generalization remains a critical challenge in deep learning-based point cloud geometry compression. While existing methods perform well on standard benchmarks, their performance collapses in real-world scenarios due to two fundamental…

Long Short-Term Memory (LSTM) neural networks have penetrated healthcare applications where real-time requirements and edge computing capabilities are essential. Gait analysis that detects abnormal steps to prevent patients from falling is…

This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the…

Acceleration of deep neural networks to meet a specific latency constraint is essential for their deployment on mobile devices. In this paper, we design an architecture aware latency constrained sparse (ALCS) framework to prune and…

We propose Adaptive Compressed Gradient Descent (AdaCGD) - a novel optimization algorithm for communication-efficient training of supervised machine learning models with adaptive compression level. Our approach is inspired by the recently…

Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a…

Large language models (LLMs) exhibit memory-intensive behavior during decoding, making it a key bottleneck in LLM inference. To accelerate decoding execution, hybrid-bonding-based 3D-DRAM has been adopted in LLM accelerators. While this…

Anomaly detection aims to separate anomalies from normal samples, and the pretrained network is promising for anomaly detection. However, adapting the pretrained features would be confronted with the risk of pattern collapse when finetuning…

Agentic artificial intelligence (AI) -- multi-agent systems that combine large language models with external tools and autonomous planning -- are rapidly transitioning from research laboratories into high-stakes domains. Our earlier "Basic"…

The Artificial Compressibility Method (ACM) for the incompressible Navier-Stokes equations is (link-wise) reformulated (referred to as LW-ACM) by a finite set of discrete directions (links) on a regular Cartesian mesh, in analogy with the…

CPU-FPGA heterogeneous architectures are attracting ever-increasing attention in an attempt to advance computational capabilities and energy efficiency in today's datacenters. These architectures provide programmers with the ability to…

Tensor algebra is a crucial component for data-intensive workloads such as machine learning and scientific computing. As the complexity of data grows, scientists often encounter a dilemma between the highly specialized dense tensor algebra…