arXiv:2507.20862v2 Announce Type: replace Abstract: Parkinson Disease (PD) often results in motor and cognitive impairments, including gait dysfunction, particularly in patients with freezing of gait (FOG). Current detection methods are either subjective or reliant on specialized gait analysis tools. This…
arXiv:2512.04198v1 Announce Type: new Abstract: A standard assumption in deep learning is that the inductive bias introduced by a neural network architecture must persist from training through inference. The architecture you train with is the architecture you deploy. This assumption…
arXiv:2512.04223v1 Announce Type: new Abstract: Modelling the complexity and diversity of human activity scheduling behaviour is inherently challenging. We demonstrate a deep conditional-generative machine learning approach for the modelling of realistic activity schedules depending on input labels such as an…
arXiv:2512.04189v1 Announce Type: new Abstract: Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well suited for deployment on resource-constrained…
arXiv:2512.04165v1 Announce Type: new Abstract: Two pressing topics in the theory of deep learning are the interpretation of feature learning mechanisms and the determination of implicit bias of networks in the rich regime. Current theories of rich feature learning effects…
arXiv:2512.04138v1 Announce Type: new Abstract: Data quality monitoring is a core challenge in modern information processing systems. While many approaches to detect data errors or shifts have been proposed, few studies investigate the mechanisms governing error generation. We argue that…
arXiv:2412.17961v2 Announce Type: replace Abstract: As graph data grows increasingly complicate, training graph neural networks (GNNs) on large-scale datasets presents significant challenges, including computational resource constraints, data redundancy, and transmission inefficiencies. While existing graph condensation techniques have shown promise in…
arXiv:2512.04264v1 Announce Type: new Abstract: Adversarial training is an effective method to improve the machine learning (ML) model robustness. Most existing studies typically consider the Rectified linear unit (ReLU) activation function and centralized training environments. In this paper, we study…
arXiv:2505.16732v3 Announce Type: replace Abstract: Optimal decision-making under partial observability requires agents to balance reducing uncertainty (exploration) against pursuing immediate objectives (exploitation). In this paper, we introduce a novel policy optimization framework for continuous partially observable Markov decision processes (POMDPs)…
arXiv:2512.04268v1 Announce Type: new Abstract: In-context learning (ICL) in large language models (LLMs) is a striking phenomenon, yet its underlying mechanisms remain only partially understood. Previous work connects linear self-attention (LSA) to gradient descent (GD), this connection has primarily been…
