model-ensemble

FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion

This repo contains the code for solving Poisson Equation using Physics Informed Neural Networks

Ensemble based transfer learning approach for accurately classifying common thoracic diseases from Chest X-Rays

This repository serves as a template for creating new projects based on FusionBench. It includes all the necessary configurations and boilerplate code to get started quickly.

Consensus Learning from Heterogeneous Objectives for One-Class Collaborative Filtering (WWW'22)

Biendata astradata competition 1st place solution. (https://www.biendata.com/competition/astrodata2019/)

Implementation of Boosting Certified $\ell_\infty$-dist Robustness with EMA Method and Ensemble Model

[網路安全的資料科學 108-2@NCCU] 惡意程式偵測 - 使用靜態分析與模型集成

To address the impact of rising house prices on the economy, we built a machine learning model resistant to market trends. We experimented with Random Forest and Linear Regression models, employing sophisticated imputation methods like median state price replacement, KNN imputation, and forward/backward filling to minimize errors.

End-to-end credit default risk prediction using feature engineering, CatBoost, validation-based early stopping, and probability blending.

TFPNER: Exploration on the Named Entity Recognition of Token Fused with Part-of-Speech

Amazon ML Challenge 2025: Multimodal Price Prediction Solution

"This repository contains implementations of Boosting method, popular techniques in Model Ensembles, aimed at improving predictive performance by combining multiple models. by using titanic database."

Real-time multi-model face analysis in Streamlit: pluggable detectors, interchangeable backends, benchmarked fusion

Archive of our RSNA Knee Abnormality Detection competition work: four final Kaggle notebook sources, reproduction notes, results, and MRI research code. Our selected submissions scored 0.958 public and 0.942 private macro AUC.

A full-stack machine learning architecture for food delivery ETA prediction, leveraging a DVC-driven pipeline, automated CI/CD workflows, cloud artifact management, and LGBM-based stacked regression ensemble for high-fidelity time estimations.

A systematic study of training recipes, data augmentation, distribution shift, and ensemble strategies for weather image classification.

Multi-model ensemble voting strategies for LLM reliability

Uncertainty-aware deep learning ensemble that turns raw Sentinel-2 imagery into georeferenced land-cover maps with per-pixel confidence - five fused segmentation models, 27 benchmarked experiments, and a decade of measured urban expansion over Vilnius.

Comparison of several machine learning classification models for a fingerprint spoofing task. Developed as academic project at Polytechnic of Turin, A.Y. 2023-24