Haifeng Xu

50 papers · 2015–2026 · 8 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🌈 Renaissance Researcher (9) 🗺️ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (8) 🏃 Academic Marathon (10) 🐝 Cross-Pollinator (6) 🔬 Deep Specialist (11) 🏆 Keyword Champion (2) 🤝 Dynamic Duo (11) 🧬 Topic Evolution 🏆 Grand Slam 👑 Triple Crown 🗃️ Keyword Collector (184) ❓ The Questioner (6) ⚡ Prolific Year (6) 💎 Century Club (49) 🔥 Unstoppable (7)

Conferences

NIPS (13) ICML (11) AAAI (10) IJCAI (8) ICLR (4) UAI (2) COLT (1) JMLR (1)

Top co-authors

Fan Yao (11) Hongning Wang (9) Chuanhao Li (7) Milind Tambe (6) Denis Nekipelov (4) Minbiao Han (3) Jibang Wu (3) Ravi Sundaram (3) Zhe Feng (3) Ashwinkumar Badanidiyuru Varadaraja (2)

Research topics

Keywords

game theory (10) online learning (6) multi-armed bandit (6) regret bound (5) mechanism design (5) stackelberg game (4) recommender system (4) multi-agent system (4) recommendation system (4) security game (4) stochastic bandit (3) poisoning attack (2) strategic classification (2) social network (2) best arm identification (2) adversarial attack (2) signaling games (2) empirical risk minimization (2) data valuation (2) adversarial learning (2)

Papers

The Publication Choice Problem AAAI 2026

Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning ICLR 2025

Learning from Imperfect Human Feedback: A Tale from Corruption-Robust Dueling ICLR 2025

Tokenized Bandit for LLM Decoding and Alignment ICML 2025

Sample Complexity of Linear Regression Models for Opinion Formation in Networks AAAI 2025

An Instrumental Value for Data Production and its Application to Data Pricing ICML 2025

Robust Optimization with Diffusion Models for Green Security UAI 2025

Mechanism Design for Large Language Models (Extended Abstract) IJCAI 2025

Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms NIPS 2024

Multi-Sender Persuasion: A Computational Perspective ICML 2024

Strategic Linear Contextual Bandits NIPS 2024

Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation ICLR 2024

Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling NIPS 2024

Learning in Online Principal-Agent Interactions: The Power of Menus AAAI 2024

Incentivized Truthful Communication for Federated Bandits ICLR 2024

Human vs. Generative AI in Content Creation Competition: Symbiosis or Conflict? ICML 2024

How Bad is Top-$K$ Recommendation under Competing Content Creators? ICML 2023

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial? NIPS 2023

The Economics of Machine Learning IJCAI 2023

PAC-learning for Strategic Classification JMLR 2023

Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts NIPS 2023

Incentivized Communication for Federated Bandits NIPS 2023

When Are Linear Stochastic Bandits Attackable? ICML 2022

Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards NIPS 2022

Inverse Game Theory for Stackelberg Games: the Blessing of Bounded Rationality NIPS 2022

CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification NIPS 2022

The Strange Role of Information Asymmetry in Auctions—Does More Accurate Value Estimation Benefit a Bidder? AAAI 2022

First-Order Convex Fitting and Its Application to Economics and Optimization AAAI 2022

Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification AAAI 2022

When Can the Defender Effectively Deceive Attackers in Security Games? AAAI 2022

Learning the Optimal Recommendation from Explorative Users AAAI 2022

Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms COLT 2022

Selling Data To a Machine Learner: Pricing via Costly Signaling ICML 2022

Learning from a Learning User for Optimal Recommendations ICML 2022

Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning IJCAI 2022

Information design for multiple independent and self-interested defenders: Work less, pay off more UAI 2022

PAC-Learning for Strategic Classification ICML 2021

The Limits of Optimal Pricing in the Dark NIPS 2021

Least Square Calibration for Peer Reviews NIPS 2021

(Almost) Free Incentivized Exploration from Decentralized Learning Agents NIPS 2021

Diffusion Source Identification on Networks with Statistical Confidence ICML 2021

The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation ICML 2020

Collapsing Bandits and Their Application to Public Health Intervention NIPS 2020

Information Shaping for Enhanced Goal Recognition of Partially-Informed Agents AAAI 2020

To Signal or Not To Signal: Exploiting Uncertain Real-Time Information in Signaling Games for Security and Sustainability AAAI 2020

Imitative Attacker Deception in Stackelberg Security Games IJCAI 2019

Don't Bury your Head in Warnings: A Game-Theoretic Approach for Intelligent Allocation of Cyber-security Alerts IJCAI 2017

Maximizing Awareness about HIV in Social Networks of Homeless Youth with Limited Information IJCAI 2017

Computing Optimal Mixed Strategies for Security Games with Dynamic Payoffs IJCAI 2015

Security Games with Information Leakage: Modeling and Computation IJCAI 2015