Optical coherence tomography angiography (OCTA) is a noninvasive, depth-resolved imaging modality that visualizes ocular microvascular networks based on blood flow-related motion contrast, without exogenous contrast agents. Owing to its ability to provide high-resolution, layer-specific vascular information, OCTA has become an indispensable tool in both clinical practice and ophthalmic research. The advent of swept-source OCTA (SS-OCTA), characterized by longer imaging wavelengths and faster scanning speeds, has enabled wider fields of view and deeper tissue penetration. These technical advances have driven the development of ultra-widefield SS-OCTA (UWF SS-OCTA), substantially enhancing visualization of the peripheral retina and anterior segment vasculature. This review outlines the fundamental principles and technological evolution of OCTA, with particular emphasis on recent progress in the clinical applications of UWF SS-OCTA across a spectrum of ophthalmic diseases. In addition, we discuss emerging opportunities for integrating artificial intelligence-based algorithms with UWF SS-OCTA to facilitate quantitative vascular analysis, disease assessment, and precision-oriented diagnosis and management.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
GAOKAO-Bench is introduced, an intuitive benchmark that employs questions from the Chinese GAOKAO examination as test samples, including both subjective and objective questions that contribute a robust evaluation benchmark for future large language models and offers valuable insights into the advantages and limitations...
Xiaotian Zhang, Chun-yan Li, Yi Zong et al.· arXiv.org· 216 citations· ⚡17
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
This work investigates the possibilities of using LLMs in a resume screening setting via a document retrieval framework that simulates job candidate selection and finds that the MTEs are biased, significantly favoring White-associated names in 85% of cases and female-associated names in only 11.1% of cases.
This work shows that orders of magnitude enhancement in performance could be obtained by a combination of hardware improvements and tight quantum-HPC integration and introduces high-performance architectures for quantum-probabilistic computing with custom-designed accelerators to tackle today's industry-scale classical...
Masoud Mohseni, Artur Scherer, K. Johnson et al.· arXiv.org· 121 citations· ⚡9