Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Xu, Lixinyu"'
LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs, but we have been unable to find work that evaluates LLM stability as the main objective. In our study of 6 deterministically configured LLMs across 8
Externí odkaz:
http://arxiv.org/abs/2408.04667
Autor:
Tang, Raphael, Zhang, Xinyu, Xu, Lixinyu, Lu, Yao, Li, Wenyan, Stenetorp, Pontus, Lin, Jimmy, Ture, Ferhan
Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how prompts affect image variability in black-box diffusion-based models. We propose W1KP, a human
Externí odkaz:
http://arxiv.org/abs/2406.08482