Stay updated with the latest research and technology news
arXiv:2602.05589v1 Announce Type: new Abstract: In this paper, a new class of \emph{Taylor-accelerated neural network interpolation operators} is introduced on quasi-uniform irregular grids. These operators...
arXiv:2602.05590v1 Announce Type: new Abstract: Immersive virtual reality (VR) applications demand accurate, temporally coherent full-body pose tracking. Recent head-mounted camera-based approaches show promise in egocentric...
arXiv:2602.05594v1 Announce Type: new Abstract: Network Intrusion Detection Systems (NIDS) have progressively shifted from signature-based techniques toward machine learning and, more recently, deep learning methods....
arXiv:2602.05596v1 Announce Type: new Abstract: With the growing employment of learning algorithms in robotic applications, research on reinforcement learning for bipedal locomotion has become a...
arXiv:2602.05597v1 Announce Type: new Abstract: Cognitive biases often shape human decisions. While large language models (LLMs) have been shown to reproduce well-known biases, a more...
arXiv:2602.05598v1 Announce Type: new Abstract: Vision Transformers (ViTs) have demonstrated strong performance across a range of computer vision tasks by modeling long-range spatial interactions via...
arXiv:2602.05599v1 Announce Type: new Abstract: Despite remarkable advances in natural language processing, developing effective systems for low-resource languages remains a formidable challenge, with performances typically...
arXiv:2602.05600v1 Announce Type: new Abstract: Stochastic Gradient Descent (SGD) introduces anisotropic noise that is correlated with the local curvature of the loss landscape, thereby biasing...
arXiv:2602.05602v1 Announce Type: new Abstract: Most existing robust fitting methods are designed for classical models, such as lines, circles, and planes. In contrast, fewer methods...
arXiv:2602.05605v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) incur prohibitive computational costs due to the quadratic scaling of self-attention. Existing pruning methods fail to simultaneously...
arXiv:2602.05608v1 Announce Type: new Abstract: Navigating through dense human crowds remains a significant challenge for mobile robots. A key issue is the freezing robot problem,...
arXiv:2602.05612v1 Announce Type: new Abstract: Federated Self-Supervised Learning (FSSL) integrates the privacy advantages of distributed training with the capability of self-supervised learning to leverage unlabeled...
arXiv:2602.05616v1 Announce Type: new Abstract: Dataset distillation compresses large datasets into compact synthetic sets with comparable performance in training models. Despite recent progress on diffusion-based...
arXiv:2602.05617v1 Announce Type: new Abstract: In this work, we introduce \textbf{XSIM}, a sensor simulation framework for autonomous driving. XSIM extends 3DGUT splatting with a generalized...
arXiv:2602.05619v1 Announce Type: new Abstract: Mode-dependent architectural components (layers that behave differently during training and evaluation, such as Batch Normalization or dropout) are commonly used...
arXiv:2602.05625v1 Announce Type: new Abstract: Exact inference in complex probabilistic models often incurs prohibitive computational costs. This challenge is particularly acute for autonomous agents in...
arXiv:2602.05628v1 Announce Type: new Abstract: Background: Empathy is widely recognized for improving patient outcomes, including reduced pain and anxiety and improved satisfaction, and its absence...
arXiv:2602.05629v1 Announce Type: new Abstract: Automated Driving System (ADS) acts as the brain of autonomous vehicles, responsible for their safety and efficiency. Safe deployment requires...
arXiv:2602.05630v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing...
arXiv:2602.05632v1 Announce Type: new Abstract: We propose a fixed-point-based numerical framework for computing stationary states of nonlocal Fokker-Planck-type equations. Instead of discretising the differential operators...
arXiv:2602.05633v1 Announce Type: new Abstract: Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce...
arXiv:2602.05635v1 Announce Type: new Abstract: Selective unlearning and long-horizon extrapolation remain fragile in modern neural networks, even when tasks have underlying algebraic structure. In this...
arXiv:2602.05636v1 Announce Type: new Abstract: Traditional ontologies excel at describing domain structure but cannot generate novel artifacts. Large language models generate fluently but produce outputs...
arXiv:2602.05638v1 Announce Type: new Abstract: While foundation models have advanced surgical video analysis, current approaches rely predominantly on pixel-level reconstruction objectives that waste model capacity...