Scholar
Leyi Pan
Google Scholar ID: 4b-1Os8AAAAJ
Tsinghua University
LLM
AI Safety
Watermark
Post Training
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
449
H-index
6
i10-index
5
Publications
12
Co-authors
16
list available
Contact
Email
panly24@mails.tsinghua.edu.cn
Twitter
Open ↗
GitHub
Open ↗
Publications
13 items
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
2026
Cited
0
mAVE: A Watermark for Joint Audio-Visual Generation Models
2026
Cited
0
Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
arXiv.org · 2026
Cited
0
Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices
arXiv.org · 2026
Cited
0
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models
2025
Cited
0
MicroRemed: Benchmarking LLMs in Microservices Remediation
2025
Cited
0
MarkDiffusion: An Open-Source Toolkit for Generative Watermarking of Latent Diffusion Models
2025
Cited
0
A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models
2025
Cited
0
Load more
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
Co-authors
16 total
Aiwei Liu
Tsinghua University
Lijie Wen(闻立杰)
Tenure Associate Professor, School of Software, Tsinghua University
Xuming Hu
Assistant Professor, HKUST(GZ) / HKUST
Philip S. Yu
Professor of Computer Science, University of Illinons at Chicago
Irwin King
The Chinese University of Hong Kong
Yijian Lu
Tsinghua University
Co-author 7
Zitian Gao
Ubiquant
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up