Deciphering the Extremes: A Novel Approach for Pathological Long-tailed Recognition in Scientific Discovery

NeurIPSSpotlight2025

Authors
Zhe Zhao, HaiBin Wen, Xianfu Liu, Rui Mao, Pengkun Wang, Liheng Yu, Linjiang Chen, Bo An, Qingfu Zhang, Yang Wang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Scientific discovery across diverse fields increasingly grapples with datasets exhibiting pathological long-tailed distributions: a few common phenomena overshadow a multitude of rare yet scientifical…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

dataset

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive