Adversarial images transfer across languages in MLLMs while apparent safety in weaker languages stems from comprehension and visual-grounding failures rather than genuine alignment.
arXiv preprint arXiv:2412.07112 , year =
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
The survey identifies a key tension in multilingual vision-language models between language neutrality via contrastive learning and cultural awareness via diverse data, with most benchmarks relying on translation-based evaluation.
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.
citing papers explorer
-
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Adversarial images transfer across languages in MLLMs while apparent safety in weaker languages stems from comprehension and visual-grounding failures rather than genuine alignment.
-
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
-
Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
A tutorial synthesizing foundations, recent models such as PALO and Maya, and low-cost methods for tri-modal multilingual AI in resource-constrained settings.