Results 91 to 100 of about 21,563 (256)

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

Probabilistic Computing via Gate‐Tunable Random Telegraph Noise

Advanced Science, EarlyView.
Intrinsic random telegraph noise in metal–oxide–semiconductor field‐effect transistors is harnessed to create gate‐tunable probabilistic bits. By modulating carrier‐trapping dynamics, the device produces stochastic binary outputs with a continuous bias‐to‐probability transfer.
Gyungwon Yun, Jin Pyo Kang, Ho‐Sung Lee, Ik‐Hyeon Jeon, Ki‐Ju Park, Won‐Ju Cho, Seung‐heon Chris Baek, Joo‐Hyung Chae, Hamin Park   +8 more
wiley   +1 more source

LLMs augmented hierarchical reinforcement learning with action primitives for long-horizon manipulation tasks

Scientific Reports
Deep reinforcement learning methods have shown promising results in learning specific tasks, but struggle to cope with the challenges of long horizon manipulation tasks.
Ning Zhang, Yongjia Zhao, Minghao Yang, Shuling Dai   +3 more
doaj   +1 more source

Probing the Energy Landscape of α‐Synuclein Amyloid Fibril Formation by Systematic K‐to‐Q Mutagenesis

Advanced Science, EarlyView.
We use lysine‐to‐glutamine mutations to study the effect of electrostatics on the kinetics and thermodynamics of alpha‐synuclein amyloid fibril formation. We find that mutational effects map on their structural context within fibrils and identify residues that modulate the energy landscape of alpha‐synuclein self‐assembly. Our work outlines a scalable,
Antonin Kunka, Azad Farzadfard, Jacob Aunstrup Larsen, Rasmus Krogh Norrild, Federica Saraceno, Celia Fricke, Hossein Mohammad‐Beigi, Ahmed Sadek, Jonas Folke, Susana Aznar, Alexander K. Buell   +10 more
wiley   +1 more source

基于UG的轿车差速器直锥齿轮专用CAD/CAM系统

Jixie chuandong, 2009
A specialized CAD/CAM system of bevel gear for car differential mechanism is developed by using the secondary development tools of UG/Open API,UG/Open UIStyler and UG/Open MenuScript,and integrated development environment Visual C++ 6.0.The system ...
陈钢, 王新云, 金俊松, 夏巨谌
doaj  

Multi-View Hypercomplex Learning for Breast Cancer Screening

IEEE Access
Radiologists interpret mammography exams by jointly analyzing all four views, as correlations among them are crucial for an accurate diagnosis. Recent methods have employed dedicated fusion blocks to capture such dependencies, but these are often ...
Eleonora Lopez, Eleonora Grassucci, Danilo Comminiello   +2 more
doaj   +1 more source

Structural Divergence Between the Moltbook AI‐Agent Network and Human Social Networks

Advanced Science, EarlyView.
Analysis of the Moltbook AI‐agent network reveals a striking combination of familiar global scaling and distinct internal organization. Attention is highly concentrated, reciprocity is limited, connected triads are suppressed, and communities are strongly modular.
Wenpin Hou, Zhicheng Ji
wiley   +1 more source

Study of the impact of load-following operation on light water reactor fuel performance using the TRANSURANUS code

Frontiers in Energy Research
Small modular reactors (SMRs) are gaining popularity due to several economic and safety benefits, along with their desirable load-following capability, which allows them to complement intermittent renewable energy sources.
Vikram Rathore, Paul Blair, Gustav Robertson, Martin Jonson, Peter Andersson   +4 more
doaj   +1 more source

Machine Learning Potential for Calcium Silicate Hydrates With Broad Compositional and Structural Diversity

Advanced Science, EarlyView.
Existing machine learning potentials remain limited in their ability to generalize across the broad chemical and structural variability of C–S–H. Here, a representative DFT‐labeled dataset is constructed through large‐scale model generation, redundancy‐controlled screening, first‐principles optimization, and targeted sampling of non‐equilibrium ...
Yunjian Li, Cheng Chen, Roland J.‐M. Pellenq, Zongjin Li, Jiaping Liu   +4 more
wiley   +1 more source

Spin Splitting Coupled Visible‐Light Driven Injection Photocurrent in Bilayer Altermagnets

Advanced Science, EarlyView.
Interlayer engineering in bilayer altermagnets continuously tunes visible‐light injection photocurrents, accompanied by controllable altermagnetic spin splitting. Enhanced interlayer hybridization reconstructs the band and quantum geometries, leading to opposite evolution of the normal and magnetic injection currents and establishing a direct ...
Huanhuan Yang, Yee Sin Ang, Sheng Meng, Xiao Jiang   +3 more
wiley   +1 more source