Xue Wang

Beyond Magnitude: Leveraging Direction of RLVR Updates for LLM Reasoning

Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs

From Weak Data to Strong Policy: Q-Targets Enable Provable In-Context Reinforcement Learning

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning

RePO: Understanding Preference Learning Through ReLU-Based Optimization

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Learning Bayesian Nash Equilibrium in Auction Games via Approximate Best Response

Larger or Smaller Reward Margins to Select Preferences for LLM Alignment?

$\alpha$-DPO: Adaptive Reward Margin is What Direct Preference Optimization Needs

Leveraging Diffusion Transformers for Stock Factor Augmentation in Financial Markets

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization