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

Changyi Li

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Vision×1NLP×1Multimedia×1Crypto×1

Frequent co-authors

Xingyu Lu1×
Jinpeng Wang1×
Yi-Fan Zhang1×
Yankai Yang1×
Yancheng Long1×
Yiyang Fan1×

Research Timeline

2026
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly

The paper introduces CyberEvolver, a self-evolving agent framework that iteratively revises its own operational scaffold based on failed execution attempts, significantly improving cybersecurity agent performance across various tasks.

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.CLRecentMay 27, 2026

VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning

Xingyu Lu, Jinpeng Wang, Yi-Fan Zhang, Yankai Yang +12 more

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multim…

View →
cs.CRcs.AIRecentMay 25, 2026

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly

Yihe Fan, Changyi Li, Lichen Xu, Xudong Pan +3 more

The paper introduces CyberEvolver, a self-evolving agent framework that iteratively revises its own operational scaffold based on failed execution attempts, significantly improving cybersecurity agent…

View →