[NeurIPS2022] Deep Model Reassembly

A curated list of Composable AI methods: Building AI system by composing modules.

Knowledge Amalgamation Engine

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

The code repository for "Model Spider: Learning to Rank Pre-Trained Models Efficiently"

Reusing Deep Neural Network Models through Model Re-engineering (ICSE'23)

Modularizing while Training: A New Paradigm for Modularizing DNN Models (ICSE'24)

Patching Weak Convolutional Neural Network Models through Modularization and Composition. (ASE'22)

A Unifying Perspective on Model Reuse: From Small to Large Pre-Trained Models (IJCAI 2025)

Code, data, and logs for paper (IJCAI 2023) 'Improving Heterogeneous Model Reuse by Density Estimation'

STARS Project: Example `simpy` model documentation using JupyterBook, GitHub Pages, and STRESS

Reusing Convolutional Neural Network Models through Modularization and Composition (TOSEM'23)

A treatment simulation model implemented in CiW

STARS Project: deploying a python DES model using streamlit

LaF focuses on the comparion testing of multiple deep learning models without manual labeling.

The official code for "Model Spider: Learning to Rank Pre-Trained Models Efficiently" (NeurIPS 2023 Spotlight)