SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.02424 · 2024

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Vision-Language Models (VLMs) integrate information from multiple modalities and have shown remarkable success across various tasks. However, deploying large-scale VLMs in resource-constrained scenarios is challenging. Pruning followed by finetuning offers a potential solution but remains underexplored for VLMs. This study addresses two key questions: how to distribute sparsity across different modality-specific models, and how to restore the performance of pruned sparse VLMs. Our preliminary studies identified two effective pruning settings: applying the same sparsity to both vision and language models, and pruning only the language models. While LoRA finetuning aims to restore sparse models, it faces challenges due to incompatibility with sparse models, disrupting the pruned sparsity. To overcome these issues, we propose SparseLoRA, which applies sparsity directly to LoRA weights. Our experimental results demonstrate significant improvements, including an 11.3\% boost under 2:4 sparsity and a 47.6\% enhancement under unstructured 70\% sparsity. Code is released at: \url{https://github.com/Shwai-He/VLM-Compression}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.02424")
get_code_for_paper("2404.02424")
have("2404.02424")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2404.02424.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2404.02424.svg)](https://syntology.ai/paper/2404.02424)

Connect an agent — have() is free.