843 citations · 847 across the 3 of their papers we have counts for
3 papers
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Rohan Anil, Sebastian Borgeaud +1340
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consist…
From Visual Attributes to Adjectives through Decompositional Distributional Semantics
Angeliki Lazaridou, Georgiana Dinu, Adam Liska +1
As automated image analysis progresses, there is increasing interest in richer linguistic annotation of pictures, with attributes of objects (e.g., furry, brown...) attracting most…
Improving zero-shot learning by mitigating the hubness problem
Georgiana Dinu, Angeliki Lazaridou, Marco Baroni
The zero-shot paradigm exploits vector-based word representations extracted from text corpora with unsupervised methods to learn general mapping functions from other feature spaces…