Related papers: AAC: Admissible-by-Architecture Differentiable Lan…
Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to…
Classifying Antimicrobial Peptides (AMPs) from the vast collection of peptides derived from metagenomic sequencing offers a promising avenue for combating antibiotic resistance. However, most existing AMP classification methods rely…
Recently, the trend of incorporating differentiable algorithms into deep learning architectures arose in machine learning research, as the fusion of neural layers and algorithmic layers has been beneficial for handling combinatorial data,…
Modern object detectors are vulnerable to adversarial examples, which brings potential risks to numerous applications, e.g., self-driving car. Among attacks regularized by $\ell_p$ norm, $\ell_0$-attack aims to modify as few pixels as…
We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and interpretability; however, learning them requires…
This research introduces a robust detection system against malicious network traffic, leveraging hierarchical structures and self-attention mechanisms. The proposed system includes a Packet Segmenter that divides a given raw network packet…
While most existing neural image compression (NIC) and neural video compression (NVC) methodologies have achieved remarkable success, their optimization is primarily focused on human visual perception. However, with the rapid development of…
Combining multiple object detection datasets offers a path to improved generalisation but is hindered by inconsistencies in class semantics and bounding box annotations. Some methods to address this assume shared label taxonomies and…
An increasingly large number of HPC systems rely on heterogeneous architectures combining traditional multi-core CPUs with power efficient accelerators. Designing efficient applications for these systems has been troublesome in the past as…
While RANSAC-based methods are robust to incorrect image correspondences (outliers), their hypothesis generators are not robust to correct image correspondences (inliers) with positional error (noise). This slows down their convergence…
Weighted Logic is a powerful tool for the specification of calculations over semirings that depend on qualitative information. Using a novel combination of Weighted Logic and Here-and-There (HT) Logic, in which this dependence is based on…
Pattern Matching is a computationally intensive task used in many research fields and real world applications. Due to the ever-growing volume of data to be processed, and increasing link speeds, the number of patterns to be matched has…
LLM-based agents increasingly rely on long-term memory to support multi-session reasoning and interaction, yet current systems provide little control over what information is retained. In practice, agents either accumulate large volumes of…
Differentiable matching layers and residual connection paradigms, often implemented via entropy-regularized Optimal Transport (OT), serve as critical mechanisms in structural prediction and architectural scaling. However, recovering…
With the development of the 3D data acquisition facilities, the increasing scale of acquired 3D point clouds poses a challenge to the existing data compression techniques. Although promising performance has been achieved in static point…
Automated design of neural network architectures tailored for a specific task is an extremely promising, albeit inherently difficult, avenue to explore. While most results in this domain have been achieved on image classification and…
Non-Exemplar Continual Graph Learning (NECGL) seeks to eliminate the privacy risks intrinsic to rehearsal-based paradigms by retaining solely class-level prototype representations rather than raw graph examples for mitigating catastrophic…
In this study, a modular, data-free pipeline for multi-label intention recognition is proposed for agentic AI applications in transportation. Unlike traditional intent recognition systems that depend on large, annotated corpora and often…
The persistent storage requirements for high-resolution, spatiotemporally evolving fields governed by large-scale and high-dimensional partial differential equations (PDEs) have reached the petabyte-to-exabyte scale. Transient simulations…
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…