Today's trail

Gradient-guided diffusion samplers provide flexible priors for inverse problems and conditional generation, but strong guidance can move the sampling trajectory into regions where the learned score is poorly supported. Existing tangent-projection strategies limit first-order…

Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains unclear when such reasoning helps or hurts. We analyze reasoning traces across models, languages, domains, and datasets, focusing on reasoning language, length, and structure. We…

Vision-language-action (VLA) models map visual observations and natural-language instructions to robotic actions, but distribution shifts can compromise their reliability. Because these models may still succeed under out-of-distribution (OOD) conditions, detecting OOD inputs…

Barren plateau diagnostics characterize whether gradient signal remains available for training, but surviving signal need not translate into successful optimization. We study this trainability--optimization gap at the level of optimizer steps. Treating coefficient-weighted…