Scholar
Yu-Xiang Wang
Google Scholar ID: HGNZ1fkAAAAJ
Associate Professor @ UC San Diego
Citations & Impact
Citations
11,372
H-index
45
i10-index
96
Publications
20
Co-authors
74
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Principal investigator on multiple NSF grants: SCALE MoDL (Adaptivity of Deep Neural Networks), CAREER (Optimal Algorithms in Differential Privacy), RI (Offline and Low-Adaptive Reinforcement Learning), and III (Neural COVID-19 Forecasting).
- 2025: Two papers accepted as Spotlights at NeurIPS'25; five papers accepted at ICML'25 on topics including data-adaptive private learning, adaptive knot selection for splines, learning under temporal distribution shift, 2:4 structured sparsity, and LLM safety.
- 2024: Six papers accepted at NeurIPS'24; six papers accepted at ICML'24 covering advances in differential privacy (private selection, neural collapse theory, parameter-efficient DP finetuning), multi-agent RL (low-adaptivity, improved sample complexity), and dynamic pricing with contextual elasticity; three papers accepted at ICLR'24.
- January 2025: Paper 'Permute-And-Flip: An Optimally Robust and Watermarkable Decoder for LLMs' accepted at ICLR'2024.
- January 2025: Paper 'Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach' accepted at AISTATS'25.
