3 papers
cs.LG2026
Scalable and Trustworthy Earth Observation Foundation Models
Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari
Foundation models (FMs) have transformed machine learning from isolated task-specific model development toward general-purpose models pretrained on broad data and adapted to multip…
cs.LG2026
PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning
Mitra Nasr Azadani, Syed Usama Imtiaz, Nasrin Alamdari
High-dimensional low-sample-size (HDLSS) datasets constrain reliable environmental model development, where labeled data remain sparse. Reinforcement learning (RL)-based adaptive s…
cs.AI2026
SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models
Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari
Foundation models are now increasingly being developed for Earth observation (EO), yet they often rely on stochastic masking that do not explicitly enforce physics constraints; a c…