LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kowsher, Md, Mansoor, Haris, Prottasha, Nusrat Jahan, Garibay, Ozlem, Zhu, Victor, Ji, Zhengping, Chen, Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914441611706368
author Kowsher, Md
Mansoor, Haris
Prottasha, Nusrat Jahan
Garibay, Ozlem
Zhu, Victor
Ji, Zhengping
Chen, Chen
author_facet Kowsher, Md
Mansoor, Haris
Prottasha, Nusrat Jahan
Garibay, Ozlem
Zhu, Victor
Ji, Zhengping
Chen, Chen
contents MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose LiME (Lightweight Mixture of Experts), which achieves expert specialization through lightweight modulation rather than adapter replication. Instead of separate adapters, LiME uses a single shared PEFT module and modulates its output with lightweight expert vectors, reducing expert parameters while generalizing to any PEFT method. Notably, LiME introduces zero-parameter routing by leveraging existing frozen and adapted representations eliminating learned router parameters typically required per layer. Theoretically, we prove that (i) more experts preserve more task-relevant information and (ii) modulation approximates full expert-specific PEFT with bounded error. LiME further incorporates n-gram windowed routing and adaptive expert selection (Auto Top-K) based on routing confidence. Experiments on MMT-47, a multimodal multi-task benchmark with 47 tasks spanning text, image, and video, demonstrate that LiME achieves competitive or superior performance while using up to 4x fewer trainable parameters and up to 29% faster training compared to corresponding MoE-PEFT baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02338
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
Kowsher, Md
Mansoor, Haris
Prottasha, Nusrat Jahan
Garibay, Ozlem
Zhu, Victor
Ji, Zhengping
Chen, Chen
Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
MoE-PEFT methods combine Mixture of Experts with parameter-efficient fine-tuning for multi-task adaptation, but require separate adapters per expert causing trainable parameters to scale linearly with expert count and limiting applicability to adapter-based architectures. We propose LiME (Lightweight Mixture of Experts), which achieves expert specialization through lightweight modulation rather than adapter replication. Instead of separate adapters, LiME uses a single shared PEFT module and modulates its output with lightweight expert vectors, reducing expert parameters while generalizing to any PEFT method. Notably, LiME introduces zero-parameter routing by leveraging existing frozen and adapted representations eliminating learned router parameters typically required per layer. Theoretically, we prove that (i) more experts preserve more task-relevant information and (ii) modulation approximates full expert-specific PEFT with bounded error. LiME further incorporates n-gram windowed routing and adaptive expert selection (Auto Top-K) based on routing confidence. Experiments on MMT-47, a multimodal multi-task benchmark with 47 tasks spanning text, image, and video, demonstrate that LiME achieves competitive or superior performance while using up to 4x fewer trainable parameters and up to 29% faster training compared to corresponding MoE-PEFT baselines.
title LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning
topic Machine Learning
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.02338