cs.CVNov 18, 2026

MoMoVL: Modality-Aware Adaptive Compression for On-Device Sparsely-Activated Vision-Language Models

Authors: Dongkeun Lee, Wonjun Lee

Organizations: Korea University Seoul, Republic of Korea · Gachon University Seongnam, Republic of Korea

Abstract

The rise of the agentic web has been accompanied by growing demand for on-device Vision-Language Models (VLMs) that perform diverse cross-modal web tasks with enhanced privacy and reduced latency. Mixture-of-Experts (MoE) models are widely adopted in modern VLMs for compute-efficient scalability, yet their multi-expert architecture poses deployment challenges due to substantial memory demands. Mixed-precision quantization is an effective compression technique that reduces bit-widths while adapting to the heterogeneous hardware budgets of edge devices, particularly well-suited for MoE due to its inherent structural sparsity, which causes imbalanced importance among experts. While prior work has applied quantization for efficient MoE inference at the edge, we point out that in MoE-based VLMs, the modality-specific characteristics of visual and text tokens further impact expert quantization. To address this issue, we present MoMoVL, a modality-aware adaptive compression framework for MoE-based VLMs that brings vision-language inference within reach of on-device resource budgets. Motivated by our empirical findings on modality-induced disparities across experts, MoMoVL jointly exploits the per-expert activation profile and per-modality quantization sensitivity to guide bit-width assignment. Experimental results show that MoMoVL improves the accuracy-compression trade-off relative to state-of-the-art mixed-precision baselines and reduces memory footprint by up to 15.44% with a modest drop in accuracy over its uniform-precision baseline. Our code and data are publicly available at https://github.com/sco-edge/MoMoVL.

Figures & tables

Explore similar work

CardsList
  1. Llama-Mobile: Efficient 2.7-Bit Quantization of VLMs

    Aug 21, 2026Luka Ribar, Jeevan Bhoot, Douglas OrrVLM QuantizationEfficient VLM Inference

  2. MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs

    Jun 15, 2026Yuanteng Chen, Peisong Wang, Zhilei Liu +9Mixed-Precision QuantizationLLM Quantization

  3. VisMMOE: Exploiting Visual-Expert Affinity for Efficient Visual-Language MoE Offloading

    May 7, 2026Cheng Xu, Xiaofeng Hou, Jiacheng Liu +1Expert OffloadingVision-Language Models