arXiv:2604. 21395v3 Announce Type: replace-cross Abstract: Ordinary supervised training minimises the task loss and then stops.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2605. 22800v3 Announce Type: replace-cross Abstract: Ordinary training optimises the task loss and then stops.
arXiv:2607. 18088v1 Announce Type: new Abstract: Standard evaluation of many recognition systems contains distribution shift by construction, since benchmarks place disjoint conditions in the training and test splits.
arXiv:2511. 02496v2 Announce Type: replace Abstract: We study latent geometry as an explicit component of representation quality in data-scarce learning.
arXiv:2503. 08038v2 Announce Type: replace-cross Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels.
arXiv:2607. 22722v1 Announce Type: cross Abstract: Almost all adversarial attacks add an imperceptible perturbation to fool a model.
arXiv:2607. 05300v1 Announce Type: new Abstract: Parameter-efficient fine-tuning still leaves a broad space of behavior-changing updates reachable, so a poisoned objective can be represented and optimized.