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

Chunyu Li

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2ML×1Software Eng.×1Crypto×1NLP×1

Frequent co-authors

Chunyu Liu1×
Mingyuan Li1×
Yang Li1×
Wenmin Li1×
Fei Gao1×
Tengfei Tu1×

Research Timeline

2026
A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty

This survey establishes persistent, writable memory as an independent security problem for LLM agents, proposing a comprehensive framework for 'mnemonic sovereignty' to govern the entire memory lifecycle.

Test Case Prioritization for DNNs via Neural Collapse Instability

This paper proposes a Neural-Collapse-Inspired Prioritization (NCIP) framework for reducing model validation costs in safety-critical domains by using cross-checkpoint prediction variability instead of absolute confidence.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.SEEmpiricalRecentJul 22, 2026

Test Case Prioritization for DNNs via Neural Collapse Instability

Chunyu Liu, Mingyuan Li, Yang Li, Wenmin Li +3 more

This paper proposes a Neural-Collapse-Inspired Prioritization (NCIP) framework for reducing model validation costs in safety-critical domains by using cross-checkpoint prediction variability instead o…

View →
cs.CRcs.AIcs.CLRecent
Apr 17, 2026

A Survey on the Security of Long-Term Memory in LLM Agents: Toward Mnemonic Sovereignty

Zehao Lin, Chunyu Li, Kai Chen

This survey establishes persistent, writable memory as an independent security problem for LLM agents, proposing a comprehensive framework for 'mnemonic sovereignty' to govern the entire memory lifecy…

View →