Abstract Model calibration usually requires optimizing some parameters (eg, temperature)
wrt an objective function like negative log-likelihood. This work uncovers a significant aspect …

The conventional evaluation protocols on machine learning models rely heavily on a
labeled, iid-assumed testing dataset, which is not often present in real world applications …

Analyzing model performance in various unseen environments is a critical research problem
in the machine learning community. To study this problem, it is important to construct a …

Today, machine learning methods are widely employed in drug discovery. However, the
chronic lack of data continues to hamper their further development, validation, and …

The guidance from capability evaluations has greatly propelled the progress of both human
society and Artificial Intelligence. However, as LLMs evolve, it becomes challenging to …

Recalling the most relevant visual memories for localisation or understanding a priori the
likely outcome of localisation effort against a particular visual memory is useful for efficient …

As large multimodal models (LMMs) are increasingly deployed across diverse applications,
the need for adaptable, real-world model ranking has become paramount. Traditional …

This work aims to develop a measure that can accurately rank the performance of various
classifiers when they are tested on unlabeled data from out-of-distribution (OOD) …

This paper adapts a general dataset representation technique to produce robust Visual
Place Recognition (VPR) descriptors, crucial to enable real-world mobile robot localisation …

Focusing on person re-identification datasets, this paper proposes a new method to estimate
the test accuracy curve over the training image number in a precise, interpretable, and …