2 papers
cs.AI2026
Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents
Mingyang Liao, Yichen Wan, shuchen wu +6
LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky o…
cs.LG2025
Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
Feifan Xia, Mingyang Liao, Yuyang Fang +6
Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogene…