Yixin Liu

10

Papers

147

Total Citations

Papers (10)

MMVU: Measuring Expert-Level Multi-Discipline Video Understanding

GOODAT: Towards Test-Time Graph Out-of-Distribution Detection

A Label-free Heterophily-guided Approach for Unsupervised Graph Fraud Detection

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention

MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning

Improving Interpretation Faithfulness for Vision Transformers

Position: TrustLLM: Trustworthiness in Large Language Models

Towards Self-Interpretable Graph-Level Anomaly Detection