Articles by Yu-Xiang Wang

Simple

Original

Articles by Yu-Xiang Wang

DPCheatSheet: Using Worked and Erroneous LLM-usage Examples to Scaffold Differential Privacy Implementation

16 September 2025 by Shao-Yu Chu and others

Human-Computer Interaction

Weak-to-Strong Jailbreaking on Large Language Models

23 July 2025 by Xuandong Zhao and others at

UC Santa Barbara

Computation and Language

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon

25 June 2025 by Tongtong Liang and others

Machine Learning

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs

23 June 2025 by Hongyi Liu and others

Machine Learning, Computation and Language

Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy

18 June 2025 by Ruihan Wu and Yu-Xiang Wang

Machine Learning, Cryptography and Security

SoK: Watermarking for AI-Generated Content

12 June 2025 by Xuandong Zhao and others at

UC Berkeley

Cryptography and Security, Artificial Intelligence

Efficiently Identifying Watermarked Segments in Mixed-Source Texts

12 June 2025 by Xuandong Zhao and others

Computation and Language

Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning

30 May 2025 by Erchi Wang and others

Machine Learning

Joint Pricing and Resource Allocation: An Optimal Online-Learning Approach

22 May 2025 by Jianyu Xu and others

Machine Learning, Optimization and Control

Adaptive Estimation and Learning under Temporal Distribution Shift

21 May 2025 by Dheeraj Baby and others

Machine Learning

Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach

9 April 2025 by Dheeraj Baby and others

Machine Learning

Purifying Approximate Differential Privacy with Randomized Post-processing

27 March 2025 by Yingyu Lin and others

Cryptography and Security, Machine Learning

Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

15 March 2025 by Xuandong Zhao and others

Computation and Language, Cryptography and Security

Square Kilometre Array Science Data Challenge 3a: foreground removal for an EoR experiment

14 March 2025 by Anna Bonaldi and others

Instrumentation and Methods for Astrophysics, Cosmology and Nongalactic Astrophysics

Dynamic Pricing with Adversarially-Censored Demands

10 February 2025 by Jianyu Xu and others

Machine Learning, Econometrics

A Proximal Operator for Inducing 2:4-Sparsity

29 January 2025 by Jonas Kübler and others

Machine Learning

No-Regret Linear Bandits under Gap-Adjusted Misspecification

9 January 2025 by Chong Liu and others

Machine Learning

Invisible Image Watermarks Are Provably Removable Using Generative AI

31 October 2024 by Xuandong Zhao and others

Cryptography and Security, Artificial Intelligence

Online Feature Updates Improve Online (Generalized) Label Shift Adaptation

31 October 2024 by Ruihan Wu and others

Machine Learning

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

30 October 2024 by Momin Haider and others

Networking and Internet Architecture, Artificial Intelligence

Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning

14 October 2024 by Chendi Wang and others

Machine Learning, Cryptography and Security

Differentially Private Bias-Term Fine-tuning of Foundation Models

19 June 2024 by Zhiqi Bu and others

Machine Learning, Computation and Language

Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes

10 June 2024 by Dan Qiao and others

Machine Learning, Artificial Intelligence

Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games

5 June 2024 by Songtao Feng and others

Machine Learning, Artificial Intelligence

Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?

18 May 2024 by Kaiqi Zhang and Yu-Xiang Wang

Machine Learning

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy

1 May 2024 by Yingyu Lin and others

Machine Learning

Offline Policy Evaluation for Reinforcement Learning with Adaptively Collected Data

1 May 2024 by Sunil Madhow and others at

UC Santa Barbara

Machine Learning, Artificial Intelligence

Differentially Private Reinforcement Learning with Self-Play

11 April 2024 by Dan Qiao and Yu-Xiang Wang

Machine Learning, Artificial Intelligence

Multivariate Trend Filtering for Lattice Data

5 April 2024 by Veeranjaneyulu Sadhanala and others

Machine Learning, Statistics Theory

CPR: Retrieval Augmented Generation for Copyright Protection

27 March 2024 by Aditya Golatkar and others

Cryptography and Security, Artificial Intelligence

Articles by Yu-Xiang Wangself.__wrap_n!=1&&self.__wrap_b("«Rkq7netetenb»",1)

Articles by Yu-Xiang Wang