Search Results for author:
Found 3 papers, 3 papers with code
Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
In this paper, we study the harmlessness alignment problem of multimodal large language models (MLLMs).
What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
By conducting a comprehensive empirical study, we find that instructions focused on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs on evaluation benchmarks.
Visually-augmented pretrained language models for NLP tasks without images
Although pre-trained language models~(PLMs) have shown impressive performance by text-only self-supervised training, they are found lack of visual semantics or commonsense.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
