Overview
Field: CV Authors: Mainak Singha, Niccolò Biondi, Elisa Ricci Published: 2026-08-11 arXiv: 2508.03799
Abstract
Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients. To this end, we propose DistMoE, a mixture-of-experts (MoE) approach for distributed visual instruction tuning.
In each layer of the language decoder, DistMoE augments the public feedforward network (FFN) with a client-specific private FFN expert, with the goal of acquiring domain-specific knowledge. However, independent expert training causes the private FFNs to learn representations of different scales and magnitudes, making merging the experts difficult.
To reduce client-specific drift, the authors introduce a public-anchored expert composition stage: the router and lightweight private projection adapters are updated only on a mixture of local client data and public data, with an isotropic regularization loss, enabling rehearsal-free composition across clients (i.e., without replaying or sharing raw private data).
During inference, DistMoE performs modular routing over public and private experts, achieving token-level domain composition without explicit domain labels. Experiments across diverse visual-language benchmarks show that DistMoE enables flexible expert reuse, effective domain adaptation, and competitive performance, while preserving modular control over client-specific knowledge.
Resources
- Paper: arXiv:2508.03799
- Code: https://github.com/mainaksingha01/DistMoE