Ziyuan Yang

The paper proposes SubPopMark, a novel subpopulation-driven framework that injects harmless, verifiable markers into distilled datasets to prevent copyright infringement and data leakage.

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss of utility.

Proposed EvoOMG framework optimizes throughput in heterogeneous Wi-Fi networks with both legacy and MLO-capable stations using an evolution-oriented multi-agent guidance approach.