Key to tasks that require reasoning about natural language in visual con...
We introduce KiloGram, a resource for studying abstract visual reasoning...
We present lilGym, a new benchmark for language-conditioned reinforcemen...
Building on recent advances in image generation, we present a fully
data...
We study continual learning for natural language instruction generation,...
Single-view 3D is the task of recovering 3D properties such as depth and...
Visual features are a promising signal for learning bootstrap textual mo...
In this paper we compare learning-based methods and classical methods fo...
We propose a new model for speaker naming in movies that leverages visua...