Humans possess an extraordinary ability to create and utilize tools. With the advent of
foundation models, artificial intelligence systems have the potential to be equally adept in …

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 …

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

Deep generative models are becoming increasingly powerful, now generating diverse high
fidelity photo-realistic samples given text prompts. Have they reached the point where …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

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 …

Massive datasets and high-capacity models have driven many recent advancements in
computer vision and natural language understanding. This work presents a platform to …

Massive web datasets play a key role in the success of large vision-language models like
CLIP and Flamingo. However, the raw web data is noisy, and existing filtering methods to …

Data is the driving force of machine learning, with the amount and quality of training data
often being more important for the performance of a system than architecture and training …

We introduce The House Of inteRactions (THOR), a framework for visual AI research,
available at http://ai2thor. allenai. org. AI2-THOR consists of near photo-realistic 3D indoor …