← Authors

Steven Wu

40 papers · 2020–2025 · 5 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (5) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (7) 🌍 Conference Polyglot (5) πŸ—ΊοΈ Taxonomy Completionist (13) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🏠 Conference Loyalist (27) πŸ”¬ Deep Specialist (12) πŸ—ƒοΈ Keyword Collector (119) ⚑ Prolific Year (8) πŸ’Ž Century Club (40) πŸ”₯ Unstoppable (6) ❓ The Questioner

Conferences

ICML (27) ICLR (7) AISTATS (3) EMNLP (2) UAI (1)

Top co-authors

Giuseppe Vietri (6) Gokul Swamy (5) Sanjiban Choudhury (4) Dung Daniel T Ngo (3) Terrance Liu (3) Drew Bagnell (3) Katrina Ligett (2) Aaditya Ramdas (2) Arindam Banerjee (2) Juba Ziani (2)

Research topics

Differential Privacy (6) Statistics (1)

Keywords

differential privacy (10) reinforcement learning (3) imitation learning (3) game theory (3) regret bound (3) causal inference (3) query release (2) federated learning (2) strategic learning (2) policy optimization (2) sample complexity (2) instrumental variable regression (2) public datum (2) large language model (2) statistical query (2) synthetic datum (2) instrumental variable (2) feature selection (1) probabilistic inference (1) non-convex optimization (1)

Papers

Predicting Language Models’ Success at Zero-Shot Probabilistic Prediction EMNLP 2025
Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Styles EMNLP 2025
Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification ICLR 2025
Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning ICLR 2025
Reconciling Model Multiplicity for Downstream Decision Making ICLR 2025
Multi-group Uncertainty Quantification for Long-form Text Generation UAI 2025
Leveraging Model Guidance to Extract Training Data from Personalized Diffusion Models ICML 2025
Kandinsky Conformal Prediction: Beyond Class- and Covariate-Conditional Coverage ICML 2025
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach ICLR 2024
Hybrid Inverse Reinforcement Learning ICML 2024
Membership Inference Attacks on Diffusion Models via Quantile Regression ICML 2024
A Minimaximalist Approach to Reinforcement Learning from Human Feedback ICML 2024
Predictive Performance Comparison of Decision Policies Under Confounding ICML 2024
Meta-Learning in Games ICLR 2023
Generating Private Synthetic Data with Genetic Algorithms ICML 2023
Inverse Reinforcement Learning without Reinforcement Learning ICML 2023
Reinforcement Learning with Stepwise Fairness Constraints AISTATS 2023
Nonparametric Extensions of Randomized Response for Private Confidence Sets ICML 2023
Fully-Adaptive Composition in Differential Privacy ICML 2023
Constrained Variational Policy Optimization for Safe Reinforcement Learning ICML 2022
Causal Imitation Learning under Temporally Correlated Noise ICML 2022
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy ICML 2022
Information Discrepancy in Strategic Learning ICML 2022
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning ICML 2022
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses ICML 2022
Improved Regret for Differentially Private Exploration in Linear MDP ICML 2022
Incentivizing Compliance with Algorithmic Instruments ICML 2021
Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization AISTATS 2021
Private Post-GAN Boosting ICLR 2021
Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification ICLR 2021
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations ICML 2021
Leveraging Public Data for Practical Private Query Release ICML 2021
Gaming Helps! Learning from Strategic Interactions in Natural Dynamics AISTATS 2021
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap ICML 2021
Privately Learning Markov Random Fields ICML 2020
New Oracle-Efficient Algorithms for Private Synthetic Data Release ICML 2020
Private Reinforcement Learning with PAC and Regret Guarantees ICML 2020
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis ICML 2020
Oracle Efficient Private Non-Convex Optimization ICML 2020
Private Query Release Assisted by Public Data ICML 2020