crisostomi/mass

Codebase for "MASS: MoErging through Adaptive Subspace Selection."

Language: Jupyter Notebook - Size: 18.7 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 4 - Forks: 1

EnnengYang/SurgeryV2

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery. Arxiv, 2024.

Language: Python - Size: 540 KB - Last synced at: 21 days ago - Pushed at: about 1 year ago - Stars: 6 - Forks: 0

AIM-SKKU/TVQ

Official repository of "Task Vector Quantization for Memory-Efficient Model Merging" [ICCV 2025]

Language: Python - Size: 3.25 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 6 - Forks: 1

fredzzhang/atlas

Official PyTorch implementation for NeurIPS'24 paper "Knowledge Composition using Task Vectors with Learned Anisotropic Scaling"

Language: Python - Size: 689 KB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 18 - Forks: 0

iurada/talos-task-arithmetic

Official repository of our work "Efficient Model Editing with Task-Localized Sparse Fine-tuning" accepted at ICLR 2025

Language: Python - Size: 84 KB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 0 - Forks: 0

nik-dim/tall_masks

Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]

Language: Python - Size: 538 KB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 34 - Forks: 0

teilomillet/operatio

Language: Mojo - Size: 2.45 MB - Last synced at: 6 months ago - Pushed at: about 1 year ago - Stars: 3 - Forks: 0

giuseppedipoce/Task-Arithmetic-Tuning-of-MobileNetV2-

This repository contain a project which goal is to find new parameter efficient fine tuning framework in order to improve performance of Deep Artificial Neural Network onto "out of distribution" data (OOD). In this specific case you can find Multi-task Learning problem.

Language: Jupyter Notebook - Size: 2.08 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 0 - Forks: 0