Xuandong Zhao
31 papers · 2021–2025 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Conference Polyglot (11) π Cross-Pollinator (10) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (8)
πΊοΈ
Taxonomy Completionist
(43)
π£
Hot Topic Early Bird
π€
Dynamic Duo
(15)
π
Triple Crown
π
Grand Slam
π₯
Mega-Team
(25)
π
Keyword Champion
(4)
π
Century Club
(31)
β‘
Prolific Year
(10)
ποΈ
Keyword Collector
(116)
π₯
Unstoppable
(5)
Conferences
ACL (6)
ICML (6)
EMNLP (5)
ICLR (5)
NAACL (2)
NIPS (2)
AAAI (1)
AACL (1)
AISTATS (1)
IJCNLP (1)
UAI (1)
Top co-authors
Research topics
Keywords
large language model
(7)
adversarial attack
(4)
text watermarking
(4)
knowledge distillation
(3)
text generation
(3)
language model
(3)
large reasoning model
(3)
watermark detection
(3)
adaptive online learning
(2)
safety assessment
(2)
text classification
(2)
prompt injection
(2)
intellectual property protection
(2)
differential privacy
(2)
ai-generated text detection
(2)
natural language inference
(1)
model distillation
(1)
online learning
(1)
attention mechanism
(1)
image generation
(1)
Papers
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
EMNLP 2025
AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
EMNLP 2025
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
AACL 2025
An Undetectable Watermark for Generative Image Models
ICLR 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
ICLR 2025
Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs
ICLR 2025
Multimodal Situational Safety
ICLR 2025
DIS-CO: Discovering Copyrighted Content in VLMs Training Data
ICML 2025
A Practical Examination of AI-Generated Text Detectors for Large Language Models
NAACL 2025
Efficiently Identifying Watermarked Segments in Mixed-Source Texts
ACL 2025
Weak-to-Strong Jailbreaking on Large Language Models
ICML 2025
Improving LLM Safety Alignment with Dual-Objective Optimization
ICML 2025
The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1
IJCNLP 2025
CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
AAAI 2025
Invisible Image Watermarks Are Provably Removable Using Generative AI
NIPS 2024
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
NIPS 2024
GumbelSoft: Diversified Language Model Watermarking via the GumbelMax-trick
ACL 2024
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
ACL 2024
Watermarking for Large Language Models
ACL 2024
MarkLLM: An Open-Source Toolkit for LLM Watermarking
EMNLP 2024
A Survey on Detection of LLMs-Generated Content
EMNLP 2024
Provable Robust Watermarking for AI-Generated Text
ICLR 2024
DE-COP: Detecting Copyrighted Content in Language Models Training Data
ICML 2024
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
ICML 2024
Pre-trained Language Models Can be Fully Zero-Shot Learners
ACL 2023
Protecting Language Generation Models via Invisible Watermarking
ICML 2023
Private Prediction Strikes Back! Private Kernelized Nearest Neighbors with Individual RΓ©nyi Filter
UAI 2023
Compressing Sentence Representation for Semantic Retrieval via Homomorphic Projective Distillation
ACL 2022
Provably Confidential Language Modelling
NAACL 2022
Distillation-Resistant Watermarking for Model Protection in NLP
EMNLP 2022
An Optimal Reduction of TV-Denoising to Adaptive Online Learning
AISTATS 2021