winners_code

The winners code of the LLM Merging Competition at NeurIPS 2025

LLM-Merging Competition at NeurIPS 2025

This repository hosts the code submissions from the winning teams of the LLM-Merging Competition at NeurIPS 2025. Congratulations to all winners for their outstanding contributions!

---

Contents

We have five winning submissions across three tracks. Each submission’s code is provided as a .tar file, named as follows:

The code are hosted on Google drive

1. Performance Track

Placement	Paper & Authors
1st Place 🌟	A Model Merging Method Qiang Gao, Jisheng Fang, Hao Mo
2nd Place ⭐	Simple Llama Merge: What Kind of LLM Do We Need? Yinuo Zhang
3rd Place 💫	LLM Merging Competition Technical Report: Efficient Model Merging with Strategic Model Selection, Merging, and Hyperparameter Optimization Zixiang Di, Yaoming Yang, Mei Jiang, Bingdong Li, Hong Qian, Aimin Zhou

2. Efficiency Track

Winner 🚀
LLM Merging Competition Technical Report for NeurIPS 2024: Efficiently Building Large Language Models through Merging Yizhen Zhang, Yang Ding, Jie Wu, Yujiu Yang

3. Most Creative Paper Write-up Track

Winner 🎆
Model Merging using Geometric Median of Task Vectors Siddharth Gupta, Aakash Gupta

---