Zesheng Shi — accepted AI-conference papers

2026

Knowledge Fusion of Large Language Models via Modular SkillPacks

Guodong DU, Zhuo Li, Xuanning Zhou, Junlin Li, Zesheng Shi, Wanyu Lin +6

ICLR 2026poster

Cross-capability transfer represents a key challenge in large language model (LLM) research, particularly in multi-task integration, model compression, and knowledge fusion. Recent works such as FuseLLM and FuseChat have shown the potential of transferring multiple model capabilities to lightweight…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Safety Alignment via Constrained Knowledge Unlearning

Zesheng Shi, Yucheng Zhou, Jing Li, Yuxin Jin, Yu Li, Daojing He +4

ACL 2025long

Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful knowledge in LLMs, which allows such attacks to bypass safeguards and produce harmful outputs. To address this challenge,…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗