218,502+ open-access research outputs.
To preserve previously learned representations, continual learning systems must strike a balance between plasticity, the ability to acquire new knowledge, and stability. This stability-plasticity dileโฆ
We use coupled-channel calculations to explore the nature of near-threshold bound states in a simplified model of Rb+KRb. This is a prototype for systems with very strong coupling at short range and cโฆ
With the widespread application of Unmanned Aerial Vehicles (UAVs) in bridge structural health monitoring, deep learning-based automatic crack detection has become a major research focus. However, praโฆ
We present a transient quantum sensing framework for cavity-magnon systems that circumvents the inevitable loss of initial-state quantum properties plaguing conventional steady-state protocols. Explicโฆ
We present a comprehensive analysis of dense cores and filamentary structures in the M16 Eagle Nebula using high-resolution ($11.7^{\prime\prime}$) surface density and temperature maps derived from \tโฆ
Surgical resection remains the only potentially curative treatment for pancreatic ductal adenocarcinoma (PDAC), and eligibility depends on accurate assessment of vascular invasion (VI), i.e., tumor exโฆ
Sand painting is a process-driven art where visual appearance emerges from granular accumulation. Given a single image, reconstructing a plausible sand painting process requires modeling coherent stroโฆ
Automated plant recognition plays a crucial role in biodiversity monitoring and conservation, yet current approaches rely heavily on supervised learning, which is limited by the availability of expertโฆ
A foundational assumption in CNN interpretability -- that deep encoders suppress background pixels while classifiers merely select from a cleaned feature pool (the Spatial Funnel Hypothesis) -- remainโฆ
Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision and graphics. However, these models still strugglโฆ
We present an extensive X-ray spectral variability study of the TeV photon-emitting high-energy-peaked BL Lacertae object PG 1553+113, using the data from EPIC-PN camera of XMM-Newton, which observed โฆ
Off-road nighttime autonomous driving suffers from unreliable visible-light perception, making infrared modality crucial for accurate freespace detection. However, progress remains limited due to the โฆ
Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency anโฆ
We study the quantum Gromov-Hausdorff convergence of spectral truncations for compact quantum groups. Using a proper length function, we define a Dirac operator and the associated spectral truncationsโฆ
Vision-Language-Action (VLA) models advance robotic control via strong visual-linguistic priors. However, existing VLAs predominantly frame pretraining as supervised behavior cloning, overlooking the โฆ
Millions of clinicians use ChatGPT to support clinical care, but evaluations of the most common use cases in model-clinician conversations are limited. We introduce HealthBench Professional, an open bโฆ
Large language models have achieved remarkable progress in text generation but still struggle with generative writing tasks. In terms of evaluation, existing benchmarks evaluate writing reward models โฆ
The reciprocality means a duality in Kirchberg algebras between K-theory groups and strong extension groups. In the paper, we will find a certain class of unital simple Exel--Laca algebras for which tโฆ
Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings,โฆ
Current density perturbations induced by radiative collapse, which is a possible mechanism governing tokamak plasma disruptions, have been investigated using a reaction-diffusion model. The reaction tโฆ
Free open-access publishing with Google Scholar indexing.
Submission Guide โ