Yixiu Mao

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models

Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning

A Unified Multi-Task Learning Framework for Generative Auto-Bidding with Validation-Aligned Optimization

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments

Adaptive HL-Gaussian: A Value Function Learning Method with Dynamic Support Adjustment

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration