SPLASH-1B: Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
This repository contains the SPLASH-1B model checkpoint presented in the paper Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs.
SPLASH-1B integrates tactile perception into vision-language models by using InternVL2.5-1B as the base MLLM backbone and a ViT-Tiny tactile frontend.
- Project Page: https://ewha-mmai.github.io/splash/
- Repository: https://github.com/ewha-mmai/splash
Description
SPLASH integrates tactile perception into vision-language models through a two-stage pipeline:
- Dormant Mask Generation: Quantifies the significance of each pretrained parameter via weight & activation importance scoring on the LLM backbone, partitioning the parameter space into a dormant and critical subspace.
- Mask-Guided Sparse Training: Updates the isolated dormant subspace to align tactile representations while freezing the critical subspace to safeguard established vision-language reasoning, preventing catastrophic forgetting.
Citation
If you find SPLASH useful, please cite the paper:
@inproceedings{park2026splash,
title={Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs},
author={Yoonhyung Park and Minji Kim and Sungwon Moon and Jiyoung Lee},
booktitle={European Conference on Computer Vision (ECCV)},
year={2026}
}