arXiv:2604.00987v1 Announce Type: cross
Abstract: We develop Structured-Knowledge-Informed Neural Networks (SKINNs), a unified estimation framework that embeds theoretical, simulated, previously learned, or cross-domain insights as differentiable cons…
arXiv:2604.00854v1 Announce Type: new
Abstract: Detecting structural chromosomal abnormalities is crucial for accurate diagnosis and management of genetic disorders. However, collecting sufficient structural abnormality data is extremely challenging a…
arXiv:2604.00168v1 Announce Type: cross
Abstract: Autonomous platforms operating in the oceans require accurate navigation to successfully complete their mission. In this regard, the initial heading estimation accuracy and the time required to achieve…
arXiv:2410.19899v2 Announce Type: replace
Abstract: Video Capsule Endoscopy (VCE) has become an indispensable diagnostic tool for gastrointestinal (GI) disorders due to its non-invasive nature and ability to capture high-resolution images of the small…
arXiv:2604.00979v1 Announce Type: cross
Abstract: Current aligned language models exhibit a dual failure mode we term the Evasive Servant: they sycophantically validate flawed user beliefs while deflecting responsibility with boilerplate disclaimers. …
arXiv:2604.00853v1 Announce Type: new
Abstract: Motion transfer enables controllable video generation by transferring temporal dynamics from a reference video to synthesize a new video conditioned on a target caption. However, existing Diffusion Trans…
arXiv:2604.00167v1 Announce Type: cross
Abstract: Automatic program repair can be a challenging task, especially when resolving complex issues at a repository-level, which often involves issue reproduction, fault localization, code repair, testing and…
arXiv:2408.06788v2 Announce Type: replace
Abstract: Visual neural decoding aims to extract and interpret original visual experiences directly from human brain activity. Recent studies have demonstrated the feasibility of decoding visual semantic categ…
arXiv:2604.00938v1 Announce Type: cross
Abstract: Transformer-based NLP models remain vulnerable to adversarial perturbations, yet existing repair methods face a fundamental trade-off: gradient-based approaches offer flexibility but lack verifiability…
arXiv:2604.00849v1 Announce Type: new
Abstract: Subject-Driven Text-to-Image (T2I) Generation aims to preserve a subject’s identity while editing its context based on a text prompt. A core challenge in this task is the “similarity-controllability para…