Results 71 to 80 of about 31,239 (262)
CLRe: A Synergistic Dual‐Engine Framework for One‐Step Retrosynthesis Prediction
Advanced Science, EarlyView.CLRe uses a contrastive difficulty score to order pretrained seq2seq fine‐tuning for retrosynthesis. Reaction embeddings define the ranking score, and a cumulative easy‐to‐hard schedule expands from the easiest subset to the full training set while earlier examples remain active.
Tianhao Su +5 more
wiley +1 more source
Bistable Networks Enable Complex Shape Changes
Advanced Science, EarlyView.Transition‐controlled metamaterials are networks of bistable mechanical memory that store local binary states and express them as global shape change. By decoupling low‐force programming from high‐force holding, a single lattice is reconfigured into distinct 2D profiles and 3D surfaces without continuous actuation, enabling reusable morphing materials ...
Sawyer Thomas, Jeffrey Lipton
wiley +1 more source
Food and Energy SecurityThis study aimed to investigate the effects of pruning period and intensity on the growth and yield of Rosa roxburghii Tratt, a shrub fruit species with significant economic value, to inform optimized pruning practices for its cultivation and management.
Yangzhou Xiang +5 more
doaj +1 more source
Breaking Down Bias: On The Limits of Generalizable Pruning Strategies
Proceedings of the 2025 ACM Conference on Fairness, Accountability, and TransparencyWe employ model pruning to examine how LLMs conceptualize racial biases, and whether a generalizable mitigation strategy for such biases appears feasible. Our analysis yields several novel insights. We find that pruning can be an effective method to reduce bias without significantly increasing anomalous model behavior.
Sibo Ma +3 more
openaire +2 more sources
Advanced Science, EarlyView.ProMetNet introduces a biologically constrained deep learning framework for proteo‐metabolomic integration by embedding Reactome‐derived pathway topology into neural networks. It captures non‐linear molecular dependencies and pathway‐level metabolic reorganization, enabling interpretable discrimination.
Minghui Zhao +6 more
wiley +1 more source
High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity
Applied SciencesRecent advancements in 3D scene representation have underscored the potential of Neural Radiance Fields (NeRFs) for producing high-fidelity renderings of complex scenes.
Shiyu Qiu +3 more
doaj +1 more source
Advanced Science, EarlyView.STWave transforms massive microscopic‐resolution spatial transcriptomics into interpretable fine‐scale tissue maps through patch‐wise inference, wavelet‐based multi‐scale encoding, and dual‐domain reconstruction. It reduces noise while preserving weak spatial signals, enabling efficient analysis of 6 40 000 spots of 2.47 GB GPU memory and revealing ...
Tao Jiang +9 more
wiley +1 more source
Aggregation and Pruning for Continuous Incremental Multi-Task Inference
MathematicsIn resource-constrained mobile systems, efficiently handling incrementally added tasks under dynamically evolving requirements is a critical challenge.
Lining Li, Fenglin Cen, Quan Feng, Ji Xu
doaj +1 more source
Effective Pruning Strategies for Sequential Pattern Mining [PDF]
First International Workshop on Knowledge Discovery and Data Mining (WKDD 2008), 2008 Xu Yusheng +3 more
openaire +2 more sources
Advanced Science, EarlyView.The protein aggregates and gene expression in the middle temporal gyrus (MTG) and somatosensory cortex (SOM) of the postmortem brains of 13 Alzheimer's disease patients were studied in detail, revealing that small hyperphosphorylated tau aggregates increase with Braak stage driven by microglial inflammation.
Elizabeth A. English +9 more
wiley +1 more source