Recorded Talks

DANIELA MASSICETI

Can few-shot approaches be used to make large multi-modal models more inclusive? 

ALAA EL-NOUBY 

Scalable Pre-training of Large Autoregressive Image Models

ELENI TRIANTAFILLOU

On challenging distribution shifts in learning and unlearning tasks 

CEES G. M. SNOEK

What multimodal foundation models cannot perceive 

RAOUL DE CHARETTE

Scene understanding on the shoulders of foundational models

STELLA YU 

Visual Intelligence Emergent from Grounding Recognition on Consistent Segmentations

MING-HSUAN YANG

Recent Results on Video Understanding and Generation via Multimodal Foundation Models

CLIFFORD BRONI-BEDIAKO

OpenEarthMap Land Cover Mapping Few-Shot Challenge Intro