Xuandong Zhao

Xuandong's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 19 papers about 12 hours ago

DE-COP: Detecting Copyrighted Content in Language Models Training Data

Paper • 2402.09910 • Published Feb 15, 2024 • 1

An undetectable watermark for generative image models

Paper • 2410.07369 • Published Oct 9, 2024

A Practical Examination of AI-Generated Text Detectors for Large Language Models

Paper • 2412.05139 • Published Dec 6, 2024

The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1

Paper • 2502.12659 • Published Feb 18, 2025 • 7

DIS-CO: Discovering Copyrighted Content in VLMs Training Data

Paper • 2502.17358 • Published Feb 24, 2025 • 1

Evaluating Durability: Benchmark Insights into Multimodal Watermarking

Paper • 2406.03728 • Published Jun 6, 2024

Improving LLM Safety Alignment with Dual-Objective Optimization

Paper • 2503.03710 • Published Mar 5, 2025 • 1

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Paper • 2503.14827 • Published Mar 19, 2025

Scalable Best-of-N Selection for Large Language Models via Self-Certainty

Paper • 2502.18581 • Published Feb 25, 2025

Assessing Judging Bias in Large Reasoning Models: An Empirical Study

Paper • 2504.09946 • Published Apr 14, 2025

Reward Shaping to Mitigate Reward Hacking in RLHF

Paper • 2502.18770 • Published Feb 26, 2025

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning

Paper • 2505.16186 • Published May 22, 2025 • 7

A Survey on Detection of LLMs-Generated Content

Paper • 2310.15654 • Published Oct 24, 2023

AgentSynth: Scalable Task Generation for Generalist Computer-Use Agents

Paper • 2506.14205 • Published Jun 17, 2025 • 8

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation

Paper • 2507.05578 • Published Jul 8, 2025 • 6

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models

Paper • 2507.07484 • Published Jul 10, 2025 • 18

AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents

Paper • 2505.05849 • Published May 9, 2025

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Paper • 2505.21347 • Published May 27, 2025 • 1

Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Paper • 2601.11868 • Published 10 days ago • 28

authored a paper 21 days ago

InfoSynth: Information-Guided Benchmark Synthesis for LLMs

Paper • 2601.00575 • Published 25 days ago • 3