Reinforcement learning (RL), particularly its combination with deep neural networks,
referred to as deep RL (DRL), has shown tremendous promise across a wide range of …

There has been an emerging paradigm shift from the era of “internet AI” to “embodied AI,”
where AI algorithms and agents no longer learn from datasets of images, videos or text …

Large language models (LLMs) and Vision-Language Models (VLMs) have been proved to
excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be …

Massive data corpora like WebText, Wikipedia, Conceptual Captions, WebImageText, and
LAION have propelled recent dramatic progress in AI. Large neural models trained on such …

We introduce SceneDiffuser, a conditional generative model for 3D scene understanding.
SceneDiffuser provides a unified model for solving scene-conditioned generation …

Goal-conditioned policies for robotic navigation can be trained on large, unannotated
datasets, providing for good generalization to real-world settings. However, particularly in …

We present the largest and most comprehensive empirical study of pre-trained visual
representations (PVRs) or visual 'foundation models' for Embodied AI. First, we curate …

Abstract We introduce Habitat 2.0 (H2. 0), a simulation platform for training virtual robots in
interactive 3D environments and complex physics-enabled scenarios. We make …

Semantic navigation is necessary to deploy mobile robots in uncontrolled environments
such as homes or hospitals. Many learning-based approaches have been proposed in …