Related papers: Comparative analysis of module-based versus direct…

Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high…

Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and…

While ordinary differential equations (ODEs) form the conceptual framework for modelling many cellular processes, specific situations demand stochastic models to capture the influence of noise. The most common formulation of stochastic…

Modulation classification, an intermediate process between signal detection and demodulation in a physical layer, is now attracting more interest to the cognitive radio field, wherein the performance is powered by artificial intelligence…

In recent years, integrating large language models (LLMs) into recommender systems has created new opportunities for improving recommendation quality. However, a comprehensive benchmark is needed to thoroughly evaluate and compare the…

For data-driven iterative learning control (ILC) methods, both the model estimation and controller design problems are converted to parameter estimation problems for some chosen model structures. It is well-known that if the model order is…

Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and item attributes. However, as privacy regulations tighten,…

Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify model behavior, they typically require extensive…

In this paper, we address the problem of reconstructing coverage maps from path-loss measurements in cellular networks. We propose and evaluate two kernel-based adaptive online algorithms as an alternative to typical offline methods. The…

Channel pruning is widely accepted to accelerate modern convolutional neural networks (CNNs). The resulting pruned model benefits from its immediate deployment on general-purpose software and hardware resources. However, its large pruning…

Deep networks are often considered to be more expressive than shallow ones in terms of approximation. Indeed, certain functions can be approximated by deep networks provably more efficiently than by shallow ones, however, no tractable…

The CLEVR dataset of natural-looking questions about 3D-rendered scenes has recently received much attention from the research community. A number of models have been proposed for this task, many of which achieved very high accuracies of…

Automatic and precise medical image segmentation (MIS) is of vital importance for clinical diagnosis and analysis. Current MIS methods mainly rely on the convolutional neural network (CNN) or self-attention mechanism (Transformer) for…

It is the goal of systems biology to understand the behavior of the whole in terms of the knowledge of the parts. This is hard to achieve in many cases due to the difficulty of characterizing the many constituents and their complex web of…

In this report, two commonly used data-driven models for predicting well production under a waterflood setting: the capacitance resistance model (CRM) and recurrent neural networks (RNN) are compared. Both models are completely data-driven…

Accurate multi-step port-of-call sequence prediction is vital for tactical resource orchestration and logistical efficiency. However, existing methods struggle with unreliable voyage schedules and the inability of AIS data to provide…

Considering patterns as sets of their instances, a difference operator over patterns computes a finite set of two given patterns, which represents the difference between the dividend pattern and the divisor pattern. A complement of a…

Music producers who use loops may have access to thousands in loop libraries, but finding ones that are compatible is a time-consuming process; we hope to reduce this burden with automation. State-of-the-art systems for estimating…

Gene regulation is a dynamic process that underlies all aspects of human development, disease response, and other key biological processes. The reconstruction of temporal gene regulatory networks has conventionally relied on regression…

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…