no code implementations • 19 Feb 2024 • Yu Zhang, Hui-Ling Zhen, Zehua Pei, Yingzhao Lian, Lihao Yin, Mingxuan Yuan, Bei Yu
In this paper, we propose a novel differential logic layer-aided language modeling (DiLA) approach, where logical constraints are integrated into the forward and backward passes of a network layer, to provide another option for LLM tool learning.
1 code implementation • NeurIPS 2021 • Lihao Yin, Ganggang Xu, Huiyan Sang, Yongtao Guan
Structured point process data harvested from various platforms poses new challenges to the machine learning community.
1 code implementation • 22 Feb 2021 • Lihao Yin, Huiyan Sang
We propose an efficient intensity estimation algorithm to estimate the spatially varying intensity function and to study the varying relationship between intensity and explanatory variables on complex domains.
Point Processes Applications Methodology
no code implementations • 22 Feb 2021 • Lihao Yin, uiyan Sang, Douglas J. Schnoebelen, Brian Wels, Don Simmons, Alyssa Mattson, Michael Schueller, Michael Pentelladan, Susie Y. Dai
We present a spatially adaptive sampling design approach based on an estimation of the spatially varying underlying contamination distribution.
Applications