Results 241 to 250 of about 15,764 (307)

INB3P: A Multi‐Modal and Interpretable Co‐Attention Framework Integrating Property‐Aware Explanations and Memory‐Bank Contrastive Fusion for Blood–Brain Barrier Penetrating Peptide Discovery

open access: yesAdvanced Science, Volume 13, Issue 34, 19 June 2026.
INB3P is a multimodal framework for blood–brain barrier‐penetrating peptide prediction under extreme data scarcity and class imbalance. By combining physicochemical‐guided augmentation, sequence–structure co‐attention, and imbalance‐aware optimization, it improves predictive performance and interpretability.
Jingwei Lv   +11 more
wiley   +1 more source

User‐Based Evaluation of Explainability Techniques for Misogyny Detection in Code‐Mixed Hindi–English

open access: yesApplied AI Letters, Volume 7, Issue 2, June 2026.
In this work, we have performed human‐based evaluation of three post hoc explainability techniques, Local Interpretable Model Agnostic Explanations (LIME), Shapely Additive Explanations (SHAP), and integrated Gradients (IG) for a multilingual Bidirectional Encoder Representations from Transformers (mBERT) based binary and multi‐label misogyny ...
Sargam Yadav   +2 more
wiley   +1 more source

From Gatekeepers to Gateways: How Acceleration and Platform Logic Reshape Life‐Science Journals

open access: yes
Learned Publishing, Volume 39, Issue 3, July 2026.
Maria Teresa Colangelo   +2 more
wiley   +1 more source

Toward Solution‐Time Advantage With Error‐Mitigated Quantum Annealing for Combinatorial Optimization

open access: yesAdvanced Physics Research, Volume 5, Issue 6, June 2026.
This paper presents a novel error mitigation technique to address the qubit errors that occur when solving combinatorial optimization problems with quantum annealing. The approach significantly speeds up the computation to reach the global optimum solution for a correlated 3D image segmentation model for material microstructures, demonstrating a ...
Yushuang Sam Yang   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy