Carl Yang

4

Papers

69

Total Citations

Papers (4)

GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning

FedSPA: Generalizable Federated Graph Learning under Homophily Heterogeneity

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

Unveiling Implicit Deceptive Patterns in Multi-Modal Fake News via Neuro-Symbolic Reasoning