Paper Detail
Bo Li, Ningyuan Deng, Tianyu Dong, Shaobo Wang, Shaolin Zhu, Lijie Wen
Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This often leads to a modality gap between visual text inputs and textual inputs/outputs for image translation. Existing methods, primarily relying on instruction fine-tuning, risk parameter redundancy of pre-trained knowledge, hindering generalization performance. To address this, we introduce modality neuron-aware fine-tuning (MNAFT), a novel approach that takes advantage of the specialized roles of individual neurons within MLLMs for enhanced image translation. MNAFT identifies language-agnostic and language-specific neurons in both vision and language modules through an instruction-driven activation analysis, evaluating their importance in various translation tasks. We then perform selective fine-tuning, updating only the parameters of language-specific and language-agnostic neurons within the selected layers relevant to the target task, while preserving the knowledge encoded in other neurons and layers. Our extensive experiments on multiple benchmarks demonstrate that MNAFT significantly outperforms state-of-the-art image translation methods, including cascaded models, standard full fine-tuning, and parameter-efficient tuning techniques. Furthermore, we provide comprehensive analysis, including visualizations of neuron activations and clustering patterns, to offer insights into the roles of different neuron groups in mediating cross-modal understanding and facilitating accurate language-specific translation.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{li2026mnaft,
title = {MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation},
author = {Bo Li and Ningyuan Deng and Tianyu Dong and Shaobo Wang and Shaolin Zhu and Lijie Wen},
year = {2026},
abstract = {Multimodal large language models (MLLMs) have shown impressive capabilities, yet they often struggle to effectively capture the fine-grained textual information within images crucial for accurate image translation. This often leads to a modality gap between visual text inputs and textual inputs/outputs for image translation. Existing methods, primarily relying on instruction fine-tuning, risk parameter redundancy of pre-trained knowledge, hindering generalization performance. To address this, we},
url = {https://huggingface.co/papers/2604.16943},
keywords = {multimodal large language models, image translation, modality gap, instruction fine-tuning, parameter redundancy, modality neuron-aware fine-tuning, language-agnostic neurons, language-specific neurons, instruction-driven activation analysis, selective fine-tuning, cross-modal understanding, huggingface daily},
eprint = {2604.16943},
archiveprefix = {arXiv},
}
{}