While neural networks are typically evaluated by their training and test performance, these metrics do not reveal how robust a learned representation is. Recent studies have shown that solutions occupying larger volumes in parameter space, as quantified by Boltzmann entropy, ofte…
Multimodal Large Language Models (MLLMs) have achieved remarkable progress but still struggle with complex visual reasoning tasks requiring multi-step perception and logical deduction. While explicit visual generation incurs prohibitive computational costs, existing latent approa…