pith. sign in

Shiyao Cui

Identifiers

  • name variant Shiyao Cui 0.60 · backfill

Papers (5)

  1. SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation cs.CV · 2026 · author #5
  2. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety cs.LG · 2026 · author #6
  3. Be Careful When Fine-tuning On Open-Source LLMs: Your Fine-tuning Data Could Be Secretly Stolen! cs.CL · 2025 · author #4
  4. How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study cs.CL · 2025 · author #6
  5. Agent-SafetyBench: Evaluating the Safety of LLM Agents cs.CL · 2024 · author #2

Mentions

  • 2606.03348 #5 · arxiv_oai · confidence 0.70 Shiyao Cui

Frequent Coauthors