Stars
✨✨Latest Advances on Multimodal Large Language Models
[NeurIPS 2025] MergeBench: A Benchmark for Merging Domain-Specialized LLMs
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
The official repository of "Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors""
Official repository for Activation-Informed Merging (AIM) of Large Language Models
PyTorch 1.11 reimplementation of multi task gradient adaptation ideas: Gradient Surgery (PCGrad) and Gradient Vaccine
A PyTorch Library for Multi-Task Learning
A comprehensive list of gradient-based multi-objective optimization algorithms in deep learning.
Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]
[ICML 2025] No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces (official repository)
Tools for merging pretrained large language models.
Model Fusion via Optimal Transport, NeurIPS 2020
Download flickr8k, flickr30k image caption datasets
An implementation of the Prompt-to-Prompt paper for the SDXL architecture
Memory Aware Synapses method implementation code
MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation
AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.
FusionBench: A Comprehensive Benchmark/Toolkit of Deep Model Fusion
[CVPR 2025] Official implementation of StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements
Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" paper.
[NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!
[NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.