On Demand, Not Uniformity: Adaptive Expert Orchestration for Multimodal Continual Instruction Tuning

Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to adapt to sequential instruction data while retaining previously acquired knowledge. While recent Mixture-of-Experts (MoE)-based methods mitigate forgetting by freezing historical experts and introducing new ones, they largely overlook the varying adaptation demands across tasks. Probing incoming tasks reveals pronounced heterogeneity in layer-wise gradient pressure and token-wise prediction difficulty. This observation highlights two unresolved decisions: where additional capacity is needed and how strongly new experts should contribute to individual tokens. To address both questions, we propose the Coverage-Calibrated Expert Injection and Residual Arbitration framework (CIRA-MoE), which derives expert acceptance margins via learnable threshold routing to serve as a unified coverage signal. Specifically, historical acceptance evidence guides the selective injection of new experts into insufficiently covered layers. Meanwhile, relative evidence between historical and current experts modulates token-wise residual contributions, coupled with arbitration-consistent regularization to promote expert specialization. Comprehensive experiments on UCIT and CoIN demonstrate that CIRA-MoE outperforms existing state-of-the-art methods in MCIT.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23865
Primary Topic
Domain Adaptation and Few-Shot Learning
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

On Demand, Not Uniformity: Adaptive Expert Orchestration for Multimodal Continual Instruction Tuning

Weitao An, Cheng Deng, Mengxin Qin, Kun Wei et al.
arXiv (Cornell University)
Domain Adaptation and Few-Shot Learning
preprint

On Demand, Not Uniformity: Adaptive Expert Orchestration for Multimodal Continual Instruction Tuning

Weitao An, Cheng Deng, Mengxin Qin, Kun Wei, Xu Yang, Jiahua Li
preprint en

Abstract

Multimodal Continual Instruction Tuning (MCIT) enables Multimodal Large Language Models (MLLMs) to adapt to sequential instruction data while retaining previously acquired knowledge. While recent Mixture-of-Experts (MoE)-based methods mitigate forgetting by freezing historical experts and introducing new ones, they largely overlook the varying adaptation demands across tasks. Probing incoming tasks reveals pronounced heterogeneity in layer-wise gradient pressure and token-wise prediction difficulty. This observation highlights two unresolved decisions: where additional capacity is needed and how strongly new experts should contribute to individual tokens. To address both questions, we propose the Coverage-Calibrated Expert Injection and Residual Arbitration framework (CIRA-MoE), which derives expert acceptance margins via learnable threshold routing to serve as a unified coverage signal. Specifically, historical acceptance evidence guides the selective injection of new experts into insufficiently covered layers. Meanwhile, relative evidence between historical and current experts modulates token-wise residual contributions, coupled with arbitration-consistent regularization to promote expert specialization. Comprehensive experiments on UCIT and CoIN demonstrate that CIRA-MoE outperforms existing state-of-the-art methods in MCIT.

arXiv (Cornell University)
Domain Adaptation and Few-Shot Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon