Chenglin Jiang — accepted AI-conference papers

2026

One for Exploration and Another for Exploitation: A Dual-Population MOEA Framework with Provable Benefits

Chenglin Jiang, Shengjie Ren, Zimin Liang, Miqing Li, Chao Qian

IJCAI 2026

Evolutionary Algorithms (EAs) are currently the most popular tool for solving multi-objective optimization problems. Balancing exploration and exploitation is fundamental to the performance of Multi-Objective EAs (MOEAs). Achieving this requires maintaining a set of high-quality solutions for effect

Cited by 0 Scholar ↗

2024

Leveraging Web-Crawled Data for High-Quality Fine-Tuning

Jing Zhou, Chenglin Jiang, Wei Shen, Xiao Zhou, Xiaonan He

EMNLP 2024finding

Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains. We argue that although the web-crawled data often has formatting errors causing semantic inaccuracies, it can still serve as a valuable…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗