Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Tianyi Xu

Tianyi Xu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

NLP×1AI×1Crypto×1

Frequent co-authors

Yaolun Zhang1×
Xuan Ouyang1×
Huazheng Wang1×
Haodong Zhao1×
Tianhang Zhao1×
Zhuosheng Zhang1×

Research Timeline

2026
GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning

GradSentry introduces a novel backdoor sample filtering method that uses the spectral entropy of individual sample gradients to detect poisoned data during LLM fine-tuning, proving effective even at high poison ratios.

EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision

EvoPool introduces an evolutionary multi-agent framework that efficiently generates high-quality, specialized supervision labels, significantly outperforming LLM annotation baselines across complex, label-scarce domains.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentJun 1, 2026

EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision

Tianyi Xu, Yaolun Zhang, Xuan Ouyang, Huazheng Wang

EvoPool introduces an evolutionary multi-agent framework that efficiently generates high-quality, specialized supervision labels, significantly outperforming LLM annotation baselines across complex, l…

View →
cs.CRRecentMay 26, 2026

GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning

Haodong Zhao, Tianyi Xu, Tianhang Zhao, Zhuosheng Zhang +1 more

GradSentry introduces a novel backdoor sample filtering method that uses the spectral entropy of individual sample gradients to detect poisoned data during LLM fine-tuning, proving effective even at h…

View →