2 papers
cs.LG2026
Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise
Minhyeok Ko, Abdollah Shafieezadeh
Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements. Under imperfect dynamics and unknown, time-varying noise statistics, this f…
cs.CL2025
Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards
Jaehoon Yun, Jiwoong Sohn, Jungwoo Park +9
Large language models have shown promise in clinical decision making, but current approaches struggle to localize and correct errors at specific steps of the reasoning process. Thi…