Results 171 to 180 of about 80,243,412 (296)

A Generalizable Framework for Building Executable Domain‐Specific Large Language Models Under Data Scarcity: Demonstration on Semiconductor Technology Computer‐Aided Design Simulation

open access: yesAdvanced Intelligent Systems, EarlyView.
A schema‐first alignment framework builds compact, executable domain‐specific language models under data scarcity. Large‐scale synthetic question‐answer generation instills domain knowledge, and a code‐centric IR‐to‐DPO pipeline aligns generation with tool‐executable syntax.
Di Wang   +4 more
wiley   +1 more source

The Collective Power of Bacteria as a Blueprint for Emergent Intelligence

open access: yesAdvanced Intelligent Systems, EarlyView.
Small cells, powerful collectives. Bacteria demonstrate how sophisticated behaviors can emerge from many simple individuals working together. We explore the remarkable world of bacterial communities and the mechanisms that underpin their complex emergent behaviors, enabling impressive adaptability, robustness, and responsiveness to changing ...
Johanna A. Blee   +2 more
wiley   +1 more source

Resilient Multimodal Fusion for Robust Vulnerability Exploitability Prediction Under Data Degradation

open access: yesAdvanced Intelligent Systems, EarlyView.
Secure Fusion‐X harmonizes unstructured NVD descriptions with structured CVSS/CWE/CPE metadata via decision‐level fusion, overcoming the fragility of traditional unimodal models. Automated assessment of software vulnerability exploitability is essential for intelligent cyber defense, yet its effectiveness is often hindered by unstable, delayed, or ...
Mona Dolati   +3 more
wiley   +1 more source

ViTAMIn‐O: Democratizing Computer Vision‐Based Machine Learning for Stem Cell Research

open access: yesAdvanced Intelligent Systems, EarlyView.
This study introduces a fully open generalist computer vision model for predicting the differentiation outcomes of stem cell‐based model systems, together with its code‐free deployment platform, ColabViTAMIn‐O. It is benchmarked against various architectures, datasets, and training protocols.
Ferhat Hamurcu   +11 more
wiley   +1 more source

Dual‐View Representation Learning for Deployable Humanoid Whole‐Body Control

open access: yesAdvanced Intelligent Systems, EarlyView.
Humanoid robots must learn control from limited onboard sensing, although simulation provides richer training‐only states. DVP learning pairs these views of each simulated motion and aligns their latent control features inside the policy‐learning loop. This direct, deployment‐aware supervision accelerates learning while the deployed policy relies only ...
Haolin Song   +3 more
wiley   +1 more source

From Instruction to Inheritance: Scaling Robot Learning Through Knowledge Circulation

open access: yesAdvanced Intelligent Systems, EarlyView.
Robot learning moves from one‐way instruction toward knowledge circulation. Humans teach robots, robots teach one another, and robots share acquired skills with humans. This perspective connects teaching, embodiment, and learning architectures to explore how knowledge is inherited, adapted, and enriched across agents, opening a path toward scalable ...
Kento Kawaharazuka   +13 more
wiley   +1 more source

Home - About - Disclaimer - Privacy