Scholar
Yaxuan Wang
Google Scholar ID: 2J96C48AAAAJ
PhD Student of Computer Science, University of California, Santa Curz
Citations & Impact
Citations
111
H-index
4
i10-index
3
Publications
7
Co-authors
0
Publications
Resume
Academic Achievements
- Paper 'Large Language Model Unlearning via Embedding-Corrupted Prompts' accepted to NeurIPS 2024
- Paper 'Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels' accepted to KDD 2025
- Preprints on arXiv: 'LLM Unlearning via Loss Adjustment with Only Forget Data' and 'Improving Data Efficiency via Curating LLM-Driven Rating Systems'
- Published 'A Complete Reinforcement-Learning-Based Framework for Urban-Safety Perception' in ISPRS International Journal of Geo-Information
- Paper 'Evaluating the Perceived Safety of Urban City via Maximum Entropy Deep Inverse Reinforcement Learning' presented at ACML 2022
- Invited talk titled 'Unlearning in LLM: A New Exploration in AI Safety' at Sichuan University in November 2024