MIRROR derives a closed-form Semi-Inverse Gromov-Wasserstein loss to align language-derived relational priors with visual representations inside decoder-only Transformers.
Vista: Enhancing vision-text alignment in mllms via cross-modal mutual in- formation maximization.arXiv preprint arXiv:2505.10917
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
VIF is a new inference-time module that maintains visual grounding in MLLMs by directly bridging pure visual representations to the output space throughout generation.
PID applied to MLLMs identifies task-specific modality interaction profiles that generalize across models, extend to tri-modal cases, and yield initial performance gains via reweighting.
citing papers explorer
-
MIRROR: Aligning Semantic Relations from Language to Image via Gromov--Wasserstein
MIRROR derives a closed-form Semi-Inverse Gromov-Wasserstein loss to align language-derived relational priors with visual representations inside decoder-only Transformers.
-
Vision Inference Former: Sustaining Visual Consistency in Multimodal Large Language Models
VIF is a new inference-time module that maintains visual grounding in MLLMs by directly bridging pure visual representations to the output space throughout generation.
-
Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition
PID applied to MLLMs identifies task-specific modality interaction profiles that generalize across models, extend to tri-modal cases, and yield initial performance gains via reweighting.