Rongsheng Li
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces PACT, a provenance-aware runtime monitor that enhances agent security by tracking the origin and trust of individual tool arguments, solving the granularity mismatch in LLM agent defenses.
The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgetting and enhancing robustness.
Papers
Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment
Ran Liu, Min Yu, Mingqi Liu, Jianguo Jiang +6 more
The paper introduces AdvCL, a framework that repurposes adversarial perturbations as a geometric control signal to stabilize continual learning in large language models, significantly reducing forgett…