Deep neural networks remain vulnerable to adversarial perturbations, which can distort not only predictions but also confidence scores, undermining uncertainty calibration. While existing certification methods focus on preserving the predicted category, providing guarantees on how calibration behaves under adversarial...
Leo Fillioux, S. Christodoulidis, Maria Vakalopoulou et al.· 0 citations
This work studies continual enterprise world model discovery, where an agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes, and builds a world model, which it revises as the rules change.
Shambhavi Mishra, David Vázquez, Perouz Taslakian et al.· 0 citations
The results suggest that skills and workflow memory can be useful in specific domains, but their apparent gains often vanish against a budget-matched actor, and that run-to-run variance materially affects outcomes and should be reported as a core evaluation criterion for online web agents.
Sina Hajimiri, Masih Aminbeidokhti, J. Dolz et al.· arXiv.org· 1 citation
PRiSM is introduced, a class-prototype regularization that can be deployed as a plug and play module on top of any existing baseline method, significantly improving performances and introducing a more realistic benchmark that varies both the levels of class balance and the effective number of classes in few-shot tasks...
Ghassen Baklouti, Omprakash Chakraborty, J. Dolz et al.· arXiv.org· 0 citations
This comprehensive survey formally defines the CTTA problem, analyzes the diverse continual domain shift patterns that characterize different evaluation protocols, and proposes a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labe...
