Related papers: Bootstrapping LLM Robustness for VLM Safety via Re…

With the increasing adoption of large language models (LLMs), ensuring the safety of LLM systems has become a pressing concern. External LLM-based guardrail models have emerged as a popular solution to screen unsafe inputs and outputs, but…

Safety hazard identification and prevention are the key elements of proactive safety management. Previous research has extensively explored the applications of computer vision to automatically identify hazards from image clips collected…

Generative medical vision-language models~(Med-VLMs) are primarily designed to generate complex textual information~(e.g., diagnostic reports) from multimodal inputs including vision modality~(e.g., medical images) and language…

Safety concerns of Multimodal large language models (MLLMs) have gradually become an important problem in various applications. Surprisingly, previous works indicate a counterintuitive phenomenon that using textual unlearning to align MLLMs…

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Fine-tuning language models is commonly believed to inevitably harm their safety, i.e., refusing to respond to harmful user requests, even when using harmless datasets, thus requiring additional safety measures. We challenge this belief…

Large vision-language models (LVLMs) have demonstrated remarkable multimodal comprehension and reasoning capabilities, but they still suffer from severe object hallucination. Previous studies primarily attribute the flaw to linguistic prior…

Large Language Models (LLMs) are transforming the robotics domain by enabling robots to comprehend and execute natural language instructions. The cornerstone benefits of LLM include processing textual data from technical manuals,…

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal…

We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs). Large-scale pre-training plays a critical role in…

Vision-language models (VLMs) can learn high-quality representations from a large-scale training dataset of image-text pairs. Prompt learning is a popular approach to fine-tuning VLM to adapt them to downstream tasks. Despite the satisfying…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images. However, their susceptibility to generating harmful content when exposed to unsafe queries raises…

Large vision-language models (LVLMs) suffer from hallucination a lot, generating responses that apparently contradict to the image content occasionally. The key problem lies in its weak ability to comprehend detailed content in a…

Large pre-trained Vision Language Models (VLMs) demonstrate excellent generalization capabilities but remain highly susceptible to adversarial examples, posing potential security risks. To improve the robustness of VLMs against adversarial…

Advances in vision-language models (VLMs) have enabled effective cross-modality retrieval. However, when both text and images exist in the database, similarity scores would differ in scale by modality. This phenomenon, known as the modality…

Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A…