Vision systems that see and reason about the compositional nature of visual scenes are
fundamental to understanding our world. The complex relations between objects and their …

Counterfactual reasoning a fundamental aspect of human cognition involves contemplating
alternatives to established facts or past events significantly enhancing our abilities in …

The diversity and complementarity of sensors available for Earth Observations (EO) calls for
developing bespoke self-supervised multimodal learning approaches. However, current …

Large language and vision-language models are rapidly being deployed in practice thanks
to their impressive capabilities in instruction following, in-context learning, and so on. This …

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone
to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our …

Self-supervised representation learning (SSL) in computer vision aims to leverage the
inherent structure and relationships within data to learn meaningful representations without …

In an era where symbolic mathematical equations are indispensable for modeling complex
natural phenomena, scientific inquiry often involves collecting observations and translating …

Spatial omics has transformed our understanding of tissue architecture by preserving spatial
context of gene expression patterns. Simultaneously, advances in imaging AI have enabled …

How can we better extract entities and relations from text? Using multimodal extraction with
images and text obtains more signals for entities and relations, and aligns them through …

Medical Vision Language Pretraining (VLP) has recently emerged as a promising solution to
the scarcity of labeled data in the medical domain. By leveraging paired/unpaired vision and …