3 papers
cs.LG2026
Uncertainty-Calibrated Spatiotemporal Field Diffusion with Sparse Supervision
Kevin Valencia, Xihaier Luo, Shinjae Yoo +1
Physical fields are typically observed only at sparse, time-varying sensor locations, making forecasting and reconstruction ill-posed and uncertainty-critical. We present SOLID, a…
cs.CV2025
Video Text Preservation with Synthetic Text-Rich Videos
Ziyang Liu, Kevin Valencia, Justin Cui
While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail…
cs.LG2025
Data-Efficient Ensemble Weather Forecasting with Diffusion Models
Kevin Valencia, Ziyang Liu, Justin Cui
Although numerical weather forecasting methods have dominated the field, recent advances in deep learning methods, such as diffusion models, have shown promise in ensemble weather…