MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.
citing papers explorer
-
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
-
Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
A plug-and-play RL method adds batch-level distributional supervision via CCC rewards to reduce regression-to-the-mean in MLLMs on imbalanced regression benchmarks.