Chao Xiang — accepted AI-conference papers

2025

Training Language Model to Critique for Better Refinement

Tianshu Yu, Chao Xiang, Mingchuan Yang, Pei Ke, Bosi Wen, Cunxiang Wang +5

ACL 2025finding

Large language models (LLMs) have demonstrated remarkable evaluation and critique capabilities, providing insightful feedback and identifying flaws in various tasks. However, limited research has explored which types of critiques are most effective for improving model responses or how to generate su…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification

Yang Liu, Weifeng Zhang, Chao Xiang, Tu Zheng, Deng Cai, Xiaofei He

CVPR 2022poster

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks, given only a few examples. To handle the limited-data in few-shot regimes, recent methods tend to collectively use a set of local features to densely represent an image instead of using a mixed gl…

Cited by 101 PDF ↗code ↗Scholar ↗