Search Results for author:
Found 2 papers, 2 papers with code
Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging
Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e. g., GPUs) or require the collection of specific training data.
FigStep: Jailbreaking Large Vision-language Models via Typographic Visual Prompts
Ensuring the safety of artificial intelligence-generated content (AIGC) is a longstanding topic in the artificial intelligence (AI) community, and the safety concerns associated with Large Language Models (LLMs) have been widely investigated.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
