Yue Wang

Disentangling Length Bias in Preference Learning via Response-Conditioned Modeling

MCCE: A Framework for Multi-LLM Collaborative Co-Evolution

ExLLM: Experience-Enhanced LLM Optimization for Molecular Design and Beyond

EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Wavelet Diffusion Neural Operator

HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting

From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control

A Probabilistic Generative Method for Safe Physical System Control Problems