Search Results for author:
Found 3 papers, 2 papers with code
Adversarial Illusions in Multi-Modal Embeddings
In this paper, we show that multi-modal embeddings can be vulnerable to an attack we call "adversarial illusions."
Hyper-Universal Policy Approximation: Learning to Generate Actions from a Single Image using Hypernets
Inspired by Gibson's notion of object affordances in human vision, we ask the question: how can an agent learn to predict an entire action policy for a novel object or environment given only a single glimpse?
On Geodesic Distances and Contextual Embedding Compression for Text Classification
On one dataset, we find that despite a 12-fold dimensionality reduction, the compressed embeddings performed within 0. 1% of the original BERT embeddings on a downstream classification task.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
