5 papers
Variational Visual Question Answering for Uncertainty-Aware Selective Prediction
Tobias Jan Wieczorek, Nathalie Daun, Mohammad Emtiyaz Khan +1
Despite remarkable progress in recent years, Vision Language Models (VLMs) remain prone to overconfidence and hallucinations on tasks such as Visual Question Answering (VQA) and Vi…
Natural Variational Annealing for Multimodal Optimization
Tâm LeMinh, Julyan Arbel, Thomas Möllenhoff +2
We introduce a new multimodal optimization approach called Natural Variational Annealing (NVA) that combines the strengths of three foundational concepts to simultaneously search f…
Knowledge Adaptation as Posterior Correction
Mohammad Emtiyaz Khan
Adaptation is the holy grail of intelligence, but even the best AI models lack the adaptability of toddlers. In spite of great progress, little is known about the mechanisms by whi…
Information Geometry of Variational Bayes
Mohammad Emtiyaz Khan
We highlight a fundamental connection between information geometry and variational Bayes (VB) and discuss its consequences for machine learning. Under certain conditions, a VB solu…
Variational Learning Induces Adaptive Label Smoothing
Sin-Han Yang, Zhedong Liu, Gian Maria Marconi +1
We show that variational learning naturally induces an adaptive label smoothing where label noise is specialized for each example. Such label-smoothing is useful to handle examples…