2 papers
cs.LG2026
Environment-Adaptive Preference Optimization for Wildfire Prediction
Enyi Jiang, Wu Sun
Predicting rare extreme events such as wildfires from meteorological data requires models that remain reliable under evolving environmental conditions. This problem is inherently l…
cs.LG2026
Latent Adversarial Regularization for Offline Preference Optimization
Enyi Jiang, Yibo Jacky Zhang, Yinglun Xu +3
Learning from human feedback typically relies on preference optimization that constrains policy updates through token-level regularization. However, preference optimization for lan…