Jarvis1111/RobustVLGuard download history

Jarvis1111/RobustVLGuard is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 32 times (2 in the last 7 days), and 804 times in total. It ranks #260,825 among datasets by monthly downloads.

🛡️ RobustVLGuard RobustVLGuard is a multimodal safety dataset designed to improve the robustness of Vision-Language Models (VLMs) against Gaussian noise and perturbation-based adversarial attacks. The dataset contains three carefully curated subsets: aligned safety data, misaligned safety

Models trained on RobustVLGuard

3 models list it as training data.

• Jarvis1111/InternVL2-8B-RobustVLGuard 15 downloads in 30 days
• Jarvis1111/llava-v1.5-7b-RobustVLGuard 11 downloads in 30 days
• Jarvis1111/MiniGPT4-RobustVLGuard – downloads in 30 days

Open Jarvis1111/RobustVLGuard on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.