Haifeng Xu

T-TAMER: Provably Taming Trade-offs in ML Serving

Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena

AI Realtor: Towards Grounded Persuasive Language Generation for Automated Copywriting

Cer-Eval: Certifiable and Cost-Efficient Evaluation Framework for LLMs

Extrapolating Large Models from the Small: Optimal Learning of Scaling Laws

Beyond Majority Voting: LLM Aggregation by Leveraging Higher-Order Information

Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?

Probabilistic Bisection Algorithm Provably Achieves Exponential Convergence

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

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

Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards

Strategic Filtering for Content Moderation: Free Speech or Free of Distortion?

Tokenized Bandit for LLM Decoding and Alignment

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