Today's trail

Online agent deployments accumulate execution trajectories at massive scale and behavioral diversity, for which predefined annotation criteria hardly exist. Extracting useful evidence therefore demands costly manual annotation or verifier signals that fail to scale, leaving…

Deep representation learning often selects hidden features and fits the final predictor on the same sample, so fixed-feature analysis performed after selection can omit selection cost. We study the conditional empirical Rademacher complexity of deep ReLU representations…

AI Few-shot forensic detection of invisible watermark attacks.

Medical image segmenters often get worse when sites, scanner vendors, or protocols change. Continual test-time adaptation (CTTA) addresses this problem without target labels, but it can be impossible to update a model on a non-stationary stream and can lead to a lot of errors.…