The recent advances in diffusion models (DMs) have revolutionized the generation of
realistic and complex images. However, these models also introduce potential safety …

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but
they also pose safety risks, such as the potential generation of harmful content and copyright …

In the evolving landscape of natural language processing (NLP), fine-tuning pre-trained
Large Language Models (LLMs) with first-order (FO) optimizers like SGD and Adam has …

With the development of foundation models such as large language models, zero-shot
transfer learning has become increasingly significant. This is highlighted by the generative …

Power efficiency is plateauing in the standard digital electronics realm such that new
hardware, models, and algorithms are needed to reduce the costs of AI training. The …

The widespread practice of fine-tuning large language models (LLMs) on domain-specific
data faces two major challenges in memory and privacy. First, as the size of LLMs continues …

Zeroth-order optimization (ZO) is a memory-efficient strategy for fine-tuning Large Language
Models using only forward passes. However, the application of ZO fine-tuning in memory …

Large language models (LLMs) have achieved impressive success in text-formatted
learning problems, and most popular LLMs have been deployed in a black-box fashion …

Parameter-efficient fine-tuning (PEFT) significantly reduces memory costs when adapting
large language models (LLMs) for downstream applications. However, traditional first-order …

As machine learning tasks continue to evolve, the trend has been to gather larger datasets
and train increasingly larger models. While this has led to advancements in accuracy, it has …