XUNGANG GU

Mr. XUNGANG GU


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2025 in Biomedical Signal Processing and Control
Verified
Journal Article
Open access
PXPengyao Xu
Pengyao Xu
LLLuyao Li
Luyao Li
XXXiaoyun Xie
Xiaoyun Xie
JLJiandong Lv
Jiandong Lv
CDChong Di
Chong Di
YCYaoyao Chen
Yaoyao Chen

5 July 2025 in Computers
Verified
Journal Article
Open access
PDF file
XGXUNGANG GU
XUNGANG GU
MWMengqi Wang
Mengqi Wang
YTYangjie Tian
Yangjie Tian
NLNing Li
Ning Li
JSJiaze Sun
Jiaze Sun
MLMing Liu
Ming Liu
Instruction tuning plays a pivotal role in aligning large language models with diverse tasks, yet its effectiveness hinges on the interplay of data quality, domain composition, and training strategies. This study moves beyond qualitative assessment to systematically quantify these factors through extensive experiments on data selection, data mixture, and training protocols. By quantifying performance trade-offs, we demonstrate that the implicit method SuperFiltering achieves an optimal balance, whereas explicit filters can induce capability conflicts. A fine-grained analysis of cross-domain interactions quantifies a near-linear competition between code and math, while showing that tool use data exhibits minimal interference. To mitigate these measured conflicts, we compare multi-task, sequential, and multi-stage training strategies, revealing that multi-stage training significantly reduces Conflict Rates while preserving domain expertise. Our findings culminate in a unified framework for optimizing instruction tuning, offering actionable, data-driven guidelines for balancing multi-domain performance and enhancing model generalization, thus advancing the field by providing a methodology to move from intuition to systematic optimization.