ES-Merging: Biological MLLM Merging via Embedding Space Signals

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Wonbin, Kim, Dongki, Hwang, Sung Ju
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917551915663360
author Lee, Wonbin
Kim, Dongki
Hwang, Sung Ju
author_facet Lee, Wonbin
Kim, Dongki
Hwang, Sung Ju
contents Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal scientific problems. While model merging is an efficient method to combine the different modalities into a unified MLLM, existing methods rely on input-agnostic parameter space heuristics that fail to faithfully capture modality specialization. To overcome this limitation, we propose the Embedding-Signal-based MLLM Merging (ES-Merging), a framework that estimates merging coefficients from embedding space signals, moving the merging paradigm from the parameter signals to the embedding signals. ES-Merging exploits coarse-grained and fine-grained signals from embedding space to estimate the layer-wise and element-wise merging coefficients, respectively, which are jointly combined for complementary coefficient estimation. Through extensive experiments, we demonstrate that ES-Merging outperforms existing merging methods not only on the cross-modal reasoning but also on the single-modal knowledge preservation, establishing that embedding space signals provide a principled and effective foundation for MLLM merging.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ES-Merging: Biological MLLM Merging via Embedding Space Signals
Lee, Wonbin
Kim, Dongki
Hwang, Sung Ju
Machine Learning
Artificial Intelligence
Biological multimodal large language models (MLLMs) have emerged as powerful foundation models for scientific discovery. However, existing models are specialized to a single modality, limiting their ability to solve inherently cross-modal scientific problems. While model merging is an efficient method to combine the different modalities into a unified MLLM, existing methods rely on input-agnostic parameter space heuristics that fail to faithfully capture modality specialization. To overcome this limitation, we propose the Embedding-Signal-based MLLM Merging (ES-Merging), a framework that estimates merging coefficients from embedding space signals, moving the merging paradigm from the parameter signals to the embedding signals. ES-Merging exploits coarse-grained and fine-grained signals from embedding space to estimate the layer-wise and element-wise merging coefficients, respectively, which are jointly combined for complementary coefficient estimation. Through extensive experiments, we demonstrate that ES-Merging outperforms existing merging methods not only on the cross-modal reasoning but also on the single-modal knowledge preservation, establishing that embedding space signals provide a principled and effective foundation for MLLM merging.
title ES-Merging: Biological MLLM Merging via Embedding Space Signals
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.14405