Results 111 to 120 of about 16,806 (262)

A Phase‐Resolved Geometric Deep Learning Framework Maps Structural Determinants of Disease‐Associated Protein Aggregation and Guides Suppressor Design

Advanced Science, EarlyView.
SKALE 2.0 maps disease‐associated protein aggregation as a phase‐resolved structural process, linking mutation‐induced geometric perturbations to nucleation, elongation, and suppressor design. Across neurodegenerative proteins, the framework reveals cryptic aggregation vulnerabilities, separates phase‐concordant and phase‐switching mutations, and ...
Jia Shen Sio, Wei Xuan Wilson Loo, Yan Shan Loo, Wen Xin Tan, Hui Xuan Lim, Huitao Liu, Chen Seng Ng   +6 more
wiley   +1 more source

Compositional Zero-Shot Learning: A Survey

CoRR
Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference, addressing the combinatorial challenge of requiring training data for every possible composition.
Ans Munir, Faisal Z. Qureshi, Mohsen Ali, Muhammad Haris Khan   +3 more
openaire   +3 more sources

Pericentrosomal Redistribution of the Endoplasmic Reticulum Ensures Organelle Symmetric Inheritance and Mitotic Progression

Advanced Science, EarlyView.
Upon mitotic entry, RTN4 relocalizes to the pericentrosomal region, forming a more tubular ER network around centrosomes. CDK1‐mediated phosphorylation of RTN4 increases its interaction with Rab11 GTPase, facilitating dynein‐dependent transport of RTN4 to the pericentrosomal region.
Xiangyu Xu, Yalin Liu, Rongyi Wang, Wenwen Xu, Hao Shi, Ning Huang, Junlin Teng, Jin Meng, Pengli Zheng, Jianguo Chen   +9 more
wiley   +1 more source

Evaluation of Few-Shot AI-Generated Feedback on Case Reports in Physical Therapy Education: Mixed Methods Study

JMIR Medical Education
BackgroundWhile artificial intelligence (AI)–generated feedback offers significant potential to overcome constraints on faculty time and resources associated with providing personalized feedback, its perceived usefulness can be ...
Hisaya Sudo, Yoko Noborimoto, Jun Takahashi   +2 more
doaj   +1 more source

AI‐Assisted Digital Single‐Molecule Activity Tracker for Decoupling Intrinsic Heterogeneity from Photo‐Oxidative Damage in High‐Photon‐Flux Enzymology

Advanced Science, EarlyView.
Employing a digital single‐molecule activity tracker (dSMAT), this research demonstrates that high‐photon‐flux irradiation drives progressive oxidative scarring in polymerases. Unlike simple thermal denaturation, real‐time kinetic tracking dynamically visualizes enzymes degrading into multiple impaired subpopulations.
Anran Zheng, Qi Yang, Jinze Li, Fuqiang Ma, Xuefeng Wang, Zhen Guo, Chuanyu Li, Dongshu Li, Jia Yao, Zhiqi Zhang, Wei Zhang, Lianqun Zhou   +11 more
wiley   +1 more source

Automating Chemical Reasoning in High‐Throughput Phase Identification With a Probabilistic, LLM‐Guided Framework

Advanced Science, EarlyView.
Autonomous laboratories can now synthesize materials faster than experts can interpret the resulting diffraction data. A probabilistic framework combines refinement‐fit metrics with large language model‐derived chemical reasoning to rank competing phase interpretations and flag those unsuitable for autonomous use.
Olympia Dartsi, Lauren N. Walters, Amalie E. Trewartha, Steven B. Torrisi, Amanda Volk, Liam Joyce, Gerbrand Ceder, Anubhav Jain   +7 more
wiley   +1 more source

Comparative Evaluation of Modern Computer Vision Models for Grasp Type Determination in Bionic Prostheses

Adaptivni Sistemi Avtomatičnogo Upravlinnâ
This research presents a comprehensive evaluation of some of the modern computer vision models for grasp type determination in bionic prostheses. The study leverages pretrained models, including CLIP and ResNet, with zero-shot and few-shot learning ...
В. Олійник, А. Верховська   +1 more
doaj   +1 more source

A Generative Neuro‐Symbolic AI for Protein Sequence Design

Advanced Science, EarlyView.
We introduce EffieDes, a neuro‐symbolic framework coupling deep learning‐based fitness landscape parameterization with exact automated reasoning. Unlike greedy sampling, EffieDes identifies sequences that globally optimize fitness while satisfying intricate design constraints.
Marianne Defresne, Delphine Dessaux, Samuel Buchet, Lucie Barthe, Liza Ammar‐Khodja, Bessam Azizi, Valentin Durante, Gianluca Cioci, Simon de Givry, Alain Roussel, Luis F. Garcia‐Alles, Thomas Schiex, Sophie Barbe   +12 more
wiley   +1 more source

SKZC: self-distillation and k-nearest neighbor-based zero-shot classification

Journal of Engineering and Applied Science
Zero-shot learning represents a formidable paradigm in machine learning, wherein the crux lies in distilling and generalizing knowledge from observed classes to novel ones.
Muyang Sun, Haitao Jia
doaj   +1 more source

Multi-Label Zero-Shot Learning With Adversarial and Variational Techniques

IEEE Access
Multi-label zero-shot learning expands upon the traditional single-label zero-shot learning paradigm by addressing the challenge of accurately classifying images containing multiple unseen classes, which are not part of the training data.
Muqaddas Gull, Omar Arif
doaj   +1 more source