Results 161 to 170 of about 11,177,407 (275)

Similarity‐Enhanced Representation Learning of Non‐Canonical Amino Acids for Therapeutic Peptide Modeling

Advanced Science, EarlyView.
Non‐canonical amino acids (ncAAs) enhance peptide therapeutics but remain difficult to model computationally. SinCAA, a similarity‐enhanced pretraining framework, jointly optimizes contrastive learning guided by a novel conformational similarity metric with masked node reconstruction, capturing both functional relationships and chemical identity of ...
Chencheng Xu, Lesong Wei, Jianmin Wang, Yuanpeng Xiong, Ruochi Zhang, Yu Wang, Chao Zha, Qiangcheng Zeng, Xin Gao   +8 more
wiley   +1 more source

Contrastive language image pretraining for a cardiac magnetic resonance image embedding with zero-shot capabilities. [PDF]

Nat Commun
Nakashima M, Qiu J, Huang P, Lee J, Chen PH, Grimm R, Nguyen C, Kim BH, Zhao D, Kwon D, Chen D.   +10 more
europepmc   +1 more source

Zero-shot distracted driver detection via vision language models with double decoupling

Distracted driving is a major cause of traffic collisions, calling for robust and scalable detection methods. Vision-language models (VLMs) enable strong zero-shot image classification, but existing VLM-based distracted driver detectors often ...
Takamichi Miyata (14580040), Andrew Morris (1258926), Sumiko Miyata (4747380)   +2 more
core  

AI‐Powered, Temperature‐Resolved Centrifugal Microfluidics for Rapid 3D Phase‐Diagram Generation of Biomolecular Condensates

Advanced Science, EarlyView.
By merging centrifugal microfluidics, precise temperature control, and AI image recognition, T‐PhaseMap transforms biomolecular condensate phase mapping into a rapid, temperature‐resolved workflow. It generates 3D composition–temperature phase diagrams within 30 min, resolves four phase states, and uncovers temperature‐dependent heparin sodium ...
Jiashuo Li, Pengjie Li, Kaiting Zhang, Yongqi Guo, Peng Chen, Bi‐Feng Liu, Yiwei Li   +6 more
wiley   +1 more source

Class-Sensitive TPB-Guided Memory Refinement for Online Zero-Shot Anomaly Detection. [PDF]

Sensors (Basel)
Zhao Z, Song F, Wang X, Yuan T, Zhou J.
europepmc   +1 more source

MethyAnno: An Interpretable Automated Annotation Method Leveraging Multi‐Scale Information and Metric Learning Framework for scDNAm Data

Advanced Science, EarlyView.
MethyAnno enables robust and interpretable annotation of single‐cell DNA methylation data by integrating multi‐scale epigenetic information, bidirectional cross‐attention, and prototype‐based metric learning. The framework resolves rare and novel cell types across datasets while revealing cell‐type‐specific epigenetic signatures associated with disease
Yuhang Jia, Siyu Li, Songming Tang, Keju Gu, Shengquan Chen   +4 more
wiley   +1 more source

Low-data cross-modal adaptation for remote sensing with proxy-enhanced multi-granularity feature caching. [PDF]

Sci Rep
Sun Y, Cheng Q, Xie W, Huang H, Gu C.
europepmc   +1 more source

Atomically Modulating Competing Exchange Interactions in Centrosymmetric Skyrmion Hosts GdRu2X2 (X = Si and Ge)

Advanced Electronic Materials, EarlyView.
Our work bridges the gap between skyrmion discovery and material design by demonstrating how atomic‐scale control of exchange interactions enables tunable skyrmion phase transitions in centrosymmetric magnetic metals. ABSTRACT Magnetic skyrmions are topologically protected spin states that hold promise for shaping the future of electronics.
Dasuni N. Rathnaweera, Xudong Huai, K. Ramesh Kumar, Michał J. Winiarski, Tomasz Klimczuk, Allana G. Iwanicki, Satya K. Kushwaha, Martin Mourigal, Tyrel M. McQueen, Thao T. Tran   +9 more
wiley   +1 more source

Visual information extraction from documents via classification-guided large vision-language models. [PDF]

Sci Rep
Li H, Chen G, Xia J, Wang L, Du W, Yao Y, Peng W, Li L.   +7 more
europepmc   +1 more source

Emerging Memory and Device Technologies for Hardware‐Accelerated Model Training and Inference

Advanced Electronic Materials, EarlyView.
This review investigates the suitability of various emerging memory technologies as compute‐in‐memory hardware for artificial intelligence (AI) applications. Distinct requirements for training‐ and inference‐centric computing are discussed, spanning device physics, materials, and system integration.
Yoonho Cho, Dae‐won Kim, Yujin Kim, Jung‐Heum Na, Yuwon Jeong, Dong‐Yeop Lee, Shinhyun Choi   +6 more
wiley   +1 more source