Stay updated with the latest research and technology news
arXiv:2603.05008v1 Announce Type: new Abstract: We present guidelines for deriving new Nitsche Finite Element Methods to enforce equality and inequality constraints that act on the...
arXiv:2603.05010v1 Announce Type: new Abstract: Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with...
arXiv:2603.05011v1 Announce Type: new Abstract: Event cameras emit asynchronous brightness-change events where each pixel triggers an event when the last event exceeds a threshold, yielding...
arXiv:2603.05012v1 Announce Type: new Abstract: Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods...
arXiv:2603.05015v1 Announce Type: new Abstract: Although virtual and augmented reality are gaining traction as teleoperation tools for various types of robots, including manipulators and mobile...
arXiv:2603.05016v1 Announce Type: new Abstract: Computational psychiatry faces a fundamental trade-off: traditional reinforcement learning (RL) models offer interpretability but lack behavioral realism, while large language...
arXiv:2603.05017v1 Announce Type: new Abstract: Navigation in cluttered environments often requires robots to tolerate contact with movable or deformable objects to maintain efficiency. Existing contact-tolerant...
arXiv:2603.05019v1 Announce Type: new Abstract: This exploratory pilot study investigates the impact of haptic perception --specifically tactile sensitivity (touch) and kinaesthetic intensity (movement)-- on learning,...
arXiv:2603.05021v1 Announce Type: new Abstract: Analyzing and controlling system entropy is a powerful tool for regulating predictability of control systems. Applications benefiting from such approaches...
arXiv:2603.05024v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) methods (SHAP, LIME) are increasingly adopted to interpret models in high-stakes businesses. However, the credibility of...
arXiv:2603.05027v1 Announce Type: new Abstract: The smart home is a key application domain within the Society 5.0 vision for a human-centered society. As smart home...
arXiv:2603.05028v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when...
arXiv:2603.05031v1 Announce Type: new Abstract: AI agents that build user interfaces on the fly assembling buttons, forms, and data displays from structured protocol payloads are...
arXiv:2603.05035v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can...
arXiv:2603.05036v1 Announce Type: new Abstract: This paper introduces the "Trilingual Triad" framework, a model that explains how students learn to design with generative artificial intelligence...
arXiv:2603.05037v1 Announce Type: new Abstract: Historical map collections are highly diverse in style, scale, and geographic focus, often consisting of many single-sheet documents. Yet most...
arXiv:2603.05040v1 Announce Type: new Abstract: Recent advancements in zero-shot commonsense reasoning have empowered Pre-trained Language Models (PLMs) to acquire extensive commonsense knowledge without requiring task-specific...
arXiv:2603.05041v1 Announce Type: new Abstract: Primary health care frequently relies on low-cost imaging devices, which are commonly used for screening purposes. To ensure accurate diagnosis,...
arXiv:2603.05042v1 Announce Type: new Abstract: Multi-camera 3D object detection (MC3D) has attracted increasing attention with the growing deployment of multi-sensor physical agents, such as robots...
arXiv:2603.05043v1 Announce Type: new Abstract: Understanding motivations of contributors for participating in community question and answer platforms is crucial for sustaining knowledge-sharing ecosystem, which is...
arXiv:2603.05044v1 Announce Type: new Abstract: Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or...
arXiv:2603.05046v1 Announce Type: new Abstract: Extending large language models to low-resource languages is essential for global accessibility, but training separate models per language is prohibitively...
arXiv:2603.05048v1 Announce Type: new Abstract: Robustness to bit errors is a key requirement for the reliable use of neural networks (NNs) on emerging approximate computing...
arXiv:2603.05053v1 Announce Type: new Abstract: Zero-shot learning (ZSL) aims to recognize unseen classes by leveraging semantic information from seen classes, but most existing methods assume...