Leyi Pan
Scholar

Leyi Pan

Google Scholar ID: 4b-1Os8AAAAJ
Tsinghua University
LLMAI SafetyWatermarkPost Training
Citations & Impact
All-time
Citations
449
 
H-index
6
 
i10-index
5
 
Publications
12
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • ACL 2025: "Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?"
  • Findings of NAACL 2025 / AAAI 2025 Workshop PDLM (Oral): "WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents"
  • EMNLP 2024 Demo: "MarkLLM: An Open-Source Toolkit for LLM Watermarking"
  • arXiv preprint: "MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models" (arXiv:2509.10569)
  • ACM Computing Surveys: "A Survey of Text Watermarking in the Era of Large Language Models" (co-first author)
  • ICLR 2025: "Can Watermarked LLMs be Identified by Users via Crafted Prompts?"
  • ICLR 2024: "A Semantic Invariant Robust Watermark for Large Language Models"
  • ICLR 2024: "An Unforgeable Publicly Verifiable Watermark for Large Language Models"
  • Contributed to GLM-4.1V-Thinking project on scalable reinforcement learning for versatile multimodal reasoning