3 papers
cs.CV2026
Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models
Weixing Wang, Liudvikas Zekas, Anton Hackl +5
Unified Multimodal Models (uMMs) aim to support both visual understanding and visual generation within a shared representation. However, existing evaluation protocols assess these…
cs.CV2026
Are We Recognizing the Jaguar or Its Background? A Diagnostic Framework for Jaguar Re-Identification
Antonio Rueda-Toicen, Abigail Allen Martin, Daniil Morozov +5
Jaguar re-identification (re-ID) from citizen-science imagery can look strong on standard retrieval metrics while still relying on the wrong evidence, such as background context or…
cs.DS2025
Minimal Algorithmic Information Loss Methods for Dimension Reduction, Feature Selection and Network Sparsification
Hector Zenil, Narsis A. Kiani, Alyssa Adams +5
We present a novel, domain-agnostic, model-independent, unsupervised, and universally applicable Machine Learning approach for dimensionality reduction based on the principles of a…