AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

Yoonhyung Park, Minji Kim, Sungwon Moon, Jiyoung Lee

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Unified any-modality language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use mask-guided dormant-subspace tuning instead of LoRA (TVL) on the same backboneQwen2.5-VL-3B · VTL averageLLM-judge score: 4.50 -> 4.91Improved
use Splash instead of LoRA on TacQuadQwen2.5-VL-3B · TacQuadLLM-judge score: 4.22 -> 4.86Improved
use Splash instead of LoRA, VL retention on MathVistaQwen2.5-VL-3B · MathVistaaccuracy: 52.8 -> 65.3Improved
use Splash instead of LoRA, VL retention on MMMUQwen2.5-VL-3B · MMMU valaccuracy: 50.0 -> 55.3Improved
tune with sparsity 100% (full LLM tuning) instead of 60% (ablation)Splash-3B · VL benchmarksMMMU val: 55.3 -> 22.0Hurt
tune with sparsity 80% instead of 60% (ablation)Splash-3B · VL benchmarksMMMU val: 55.3 -> 52.6Hurt
lower sparsity 30% instead of 60% (ablation)Splash-3B · VTL averageLLM-judge score: 4.91 -> 4.79Hurt
calibrate mask with unpaired noise images instead of CC3M paired (ablation)Splash-3B · VTL averageLLM-judge score: 4.91 -> 4.88No clear effect
calibrate with TVL paired data instead of CC3M (ablation)Splash-3B · VTL averageLLM-judge score: 4.91 -> 4.75No clear effect
use uniform sparsity instead of OWL adaptive layer-wise sparsity (ablation)Splash-3B · VTL averageLLM-judge score: 4.83 -> 4.91Improved
freeze first and last transformer blocks (ablation)Splash-3B · VTL averageLLM-judge score: 0.18 point drop when unfrozenImproved
use Splash instead of (IA)3 on TacQuadQwen2.5-VL-3B · TacQuadLLM-judge score: 3.84 -> 4.86Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy