no code implementations • 14 Mar 2024 • Tianshuo Xu, Peng Mi, Ruilin Wang, Yingcong Chen
In this paper, we start with a consistency phenomenon of DMs: we observe that DMs with different initializations or even different architectures can produce very similar outputs given the same noise inputs, which is rare in other generative models.
2 code implementations • 23 Aug 2023 • Ziyi Tang, Ruilin Wang, Weixing Chen, Keze Wang, Yang Liu, Tianshui Chen, Liang Lin
Despite advancements in LLMs, knowledge-based reasoning remains a longstanding issue due to the fragility of knowledge recall and inference.