3 papers
cs.LG2026
Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
Mengdi Chu, Yang Liu, Ayan Biswas +1
Recent physics foundation models claim general spatiotemporal forecasting ability, yet their evaluations often collapse performance into a single average score under a fixed traini…
cs.HC2026
DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data
Mengdi Chu, Jiaxin Yang, Angus G. Forbes +4
Modeling temporal evolution is important to analyzing and reasoning about scientific phenomena, yet most machine learning methods provide deterministic forward predictions that ove…
cs.LG2026
Refine Now, Query Fast: A Decoupled Refinement Paradigm for Implicit Neural Fields
Tianyu Xiong, Skylar Wurster, Han-Wei Shen
Implicit Neural Representations (INRs) have emerged as promising surrogates for large 3D scientific simulations due to their ability to continuously model spatial and conditional f…