Pre-trained vision models (PVMs) have become a dominant component due to their
exceptional performance when fine-tuned for downstream tasks. However, the presence of …

Large Language Models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …

Abstract Reinforcement Learning with Human Feedback (RLHF) is a methodology designed
to align Large Language Models (LLMs) with human preferences, playing an important role …

Despite being widely applied due to their exceptional capabilities, Large Language Models
(LLMs) have been proven to be vulnerable to backdoor attacks. These attacks introduce …

Large language models (LLMs) have raised concerns about potential security threats
despite performing significantly in Natural Language Processing (NLP). Backdoor attacks …

Thanks to the explosive growth of data and the development of computational resources, it is
possible to build pre-trained models that can achieve outstanding performance on various …

Large Language Models (LLMs), which bridge the gap between human language
understanding and complex problem-solving, achieve state-of-the-art performance on …