Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

StackingNet: Collective Inference Across Independent AI Foundation Models.

Siyang Li¹, Chenhao Liu¹, Dongrui Wu¹

¹School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)

|July 9, 2026

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

The microbial nexus: linking arsenic biogeochemistry with greenhouse gas emissions.

Frontiers in microbiology·2026

Same author

Performance of lunar shell structure for moonbase subjected to low gravity coupled with changing temperature.

Fundamental research·2026

Same author

CKD: Contrastive Knowledge Distillation for Cross-Dataset EEG Classification.

IEEE transactions on bio-medical engineering·2026

Same author

Qijia Rougan Formula alleviates liver fibrosis by inhibiting NLRP3-mediated pyroptosis and regulating macrophage polarization.

Frontiers in immunology·2026

Same author

fastSeizureNet: Accurate and efficient knowledge-data fusion for semi-supervised seizure detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Transcriptome data combined with two-sample Mendelian randomization reveal IRF1 and PRKD1 as UPR-related key regulators in intervertebral disc degeneration.

Medicine·2026

StackingNet, a new meta-ensemble framework, enables coordination between diverse artificial intelligence (AI) foundation models. This approach enhances AI performance and reliability without needing internal model access.

Area of Science:

Artificial Intelligence
Machine Learning
Ensemble Methods

Background:

Foundation models in AI excel in specific tasks but operate in isolation.
Coordinating diverse, black-box AI models is crucial for trustworthy intelligent systems.
Existing methods lack a framework for effective collaboration among independent AI models.

Purpose of the Study:

To introduce StackingNet, a meta-ensemble framework for coordinating independent foundation models.
To demonstrate StackingNet's ability to aggregate predictions and improve overall AI performance.
To validate StackingNet's effectiveness across various AI domains without internal model access.

Main Methods:

Developed StackingNet, a meta-ensemble framework that aggregates predictions from independent foundation models at inference.

Keywords:

artificial intelligence ensemble learning foundation model large language model machine learning vision language model

Related Experiment Videos

Applied StackingNet to tasks including language comprehension, visual attribute estimation, and academic paper rating.

Evaluated StackingNet's performance against individual models and traditional ensembles.

Main Results:

StackingNet consistently improved accuracy and reduced errors compared to individual models.
The framework effectively ranked model reliability and identified underperforming models.
Performance gains were attributed to variance reduction and consensus alignment, increasing with model diversity.

Conclusions:

StackingNet provides a practical method for coordinating specialized AI models, fostering cooperation.
This approach enhances AI capabilities by leveraging model diversity as a resource.
Future AI progress can emerge from principled cooperation among multiple specialized models, not just larger single models.