When and Where to Trust the Teacher: Unifying On-Policy Distillation and GRPO through Entropy-Calibrated Credit AssignmentResearchSep 24, 2026
Resource-Adaptive Stochastic Gradient Descent for Online Linear Programming without Re-solvingResearchSep 24, 2026
Physiologically Informed Digital Auscultation for Pneumonia Detection in Long-term Care ResidentsResearchSep 24, 2026
HIVE: Hidden-Evidence Verification for Hallucination Detection in Diffusion Large Language ModelsResearchSep 24, 2026