Stay updated with the latest research and technology news
arXiv:2602.17493v1 Announce Type: new Abstract: We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly...
arXiv:2602.17494v1 Announce Type: new Abstract: The TV-Stokes model is a two-step variational method for image denoising that combines the estimation of a divergence-free tangent field...
arXiv:2602.17497v1 Announce Type: new Abstract: Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates...
arXiv:2602.17498v1 Announce Type: new Abstract: Natural Language Processing (NLP) tools support requirements engineering (RE) tasks like requirements elicitation, classification, and validation. However, they are often...
arXiv:2602.17502v1 Announce Type: new Abstract: Lower limb amputation affects millions worldwide, leading to impaired mobility, reduced walking speed, and limited participation in daily and social...
arXiv:2602.17504v1 Announce Type: new Abstract: Many unmanned aerial vehicles (UAVs) can remain aerodynamically flyable after sustaining structural or control surface damage, yet insufficient robustness in...
arXiv:2602.17507v1 Announce Type: new Abstract: The aim of this work is to apply a semi-implicit (SI) strategy within a Rosenbrock-type and IMEX linear multistep (LM)...
arXiv:2602.17508v1 Announce Type: new Abstract: This work presents a practical benchmarking framework for optimizing artificial intelligence (AI) models on ARM Cortex processors (M0+, M4, M7),...
arXiv:2602.17510v1 Announce Type: new Abstract: We introduce CRAFT (Cross-layer Rank Adaptation via Frozen Tucker), a parameter-efficient fine-tuning (PEFT) method that applies Tucker tensor decomposition to...
arXiv:2602.17512v1 Announce Type: new Abstract: The sudden appearance of a static obstacle on the road, i.e. the moose test, is a well-known emergency scenario in...
arXiv:2602.17513v1 Announce Type: new Abstract: Clinical free-text notes contain vital patient information. They are structured into labelled sections; recognizing these sections has been shown to...
arXiv:2602.17515v1 Announce Type: new Abstract: Existing aerial robot navigation systems typically plan paths around static and dynamic obstacles, but fail to adapt when a static...
arXiv:2602.17516v1 Announce Type: new Abstract: We present a new method for computing the action of the matrix exponential on a vector, $e^{At}v$. The proposed approach...
arXiv:2602.17517v1 Announce Type: new Abstract: Augmented reality can improve tumor localization in laparoscopic liver surgery. Existing registration pipelines typically depend on organ contours; deformable (non-rigid)...
arXiv:2602.17518v1 Announce Type: new Abstract: With automated systems increasingly issuing search queries alongside humans, Information Retrieval (IR) faces a major shift. Yet IR remains human-centred,...
arXiv:2602.17520v1 Announce Type: new Abstract: Large language models (LLMs) demonstrate strong performance on standard digital logic and Boolean reasoning tasks, yet their reliability under locally...
arXiv:2602.17525v1 Announce Type: new Abstract: In variational inference (VI), the practitioner approximates a high-dimensional distribution $\pi$ with a simple surrogate one, often a (product) Gaussian...
arXiv:2602.17526v1 Announce Type: new Abstract: Some transformer attention heads appear to function as membership testers, dedicating themselves to answering the question "has this token appeared...
arXiv:2602.17529v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential across a variety of tasks, but their application in the telecom field...
arXiv:2602.17530v1 Announce Type: new Abstract: Despite significant progress in post-hoc explanation methods for neural networks, many remain heuristic and lack provable guarantees. A key approach...
arXiv:2602.17531v1 Announce Type: new Abstract: This position paper argues that current benchmarking practice in 12-lead ECG representation learning must be fixed to ensure progress is...
arXiv:2602.17535v1 Announce Type: new Abstract: Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging, but their reliability under domain shift hinges on calibrated...
arXiv:2602.17537v1 Announce Type: new Abstract: Robotic camera systems enable dynamic, repeatable motion beyond human capabilities, yet their adoption remains limited by the high cost and...
arXiv:2602.17541v1 Announce Type: new Abstract: We study the self-stabilizing leader election problem in anonymous $n$-nodes networks. Achieving self-stabilization with low space memory complexity is particularly...