Leyi Pan
7 papers · 2024–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(15)
❓
The Questioner
(2)
Top co-authors
Research topics
Keywords
large language model
(3)
text watermarking
(3)
watermark detection
(2)
text generation detection
(2)
false positive rate
(1)
semantic embedding
(1)
ai-generated text detection
(1)
watermark removal
(1)
model protection
(1)
watermark radioactivity
(1)
paraphrasing training
(1)
diffusion language model
(1)
neural network
(1)
synonym substitution
(1)
attack robustness
(1)
detection algorithm
(1)
llm-generated text
(1)
llm watermarking
(1)
segment detection
(1)
watermarking detection
(1)
Papers
d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models
ACL 2026
Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
ACL 2025
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
ICLR 2025
WaterSeeker: Pioneering Efficient Detection of Watermarked Segments in Large Documents
NAACL 2025
An Unforgeable Publicly Verifiable Watermark for Large Language Models
ICLR 2024
A Semantic Invariant Robust Watermark for Large Language Models
ICLR 2024
MarkLLM: An Open-Source Toolkit for LLM Watermarking
EMNLP 2024