Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
What do navigation agents learn about their environment?
Today’s state of the art visual navigation agents typically consist of large deep learning models trained end to end. Such models offer little to no interpretability about the learned skills or the…
Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks
We propose Unified-IO, a model that performs a large variety of AI tasks spanning classical computer vision tasks, including pose estimation, object detection, depth estimation and image generation,…
DeepA2: A Modular Framework for Deep Argument Analysis with Pretrained Neural Text2Text Language Models
In this paper, we present and implement a multi-dimensional, modular framework for performing deep argument analysis (DeepA2) using current pre-trained language models (PTLMs). ArgumentAnalyst – a…
Correcting a coarse-grid climate model in multiple climates by machine learning from global 25-km resolution simulations
Bretherton et al. (2022, https://doi.org/10.1029/2021MS002794) demonstrated a successful approach for using machine learning (ML) to help a coarse-resolution global atmosphere model with real…
Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity
We present a new scientific document similarity model based on matching fine-grained aspects of texts. To train our model, we exploit a naturally-occurring source of supervision: sentences in the…
A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge
The Visual Question Answering (VQA) task aspires to provide a meaningful testbed for the development of AI models that can jointly reason over visual and natural language inputs. Despite a…
VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
Accurately extracting structured content from PDFs is a critical first step for NLP over scientific papers. Recent work has improved extraction accuracy by incorporating elementary layout…
What Language Model to Train if You Have One Million GPU Hours?
The crystallization of modeling methods around the Transformer architecture has been a boon for practitioners. Simple, well-motivated architectural variations that transfer across tasks and scale,…
Retrieval Data Augmentation Informed by Downstream Question Answering Performance
Training retrieval models to fetch contexts for Question Answering (QA) over large corpora requires labeling relevant passages in those corpora. Since obtaining exhaustive manual annotations of all…
Quark: Controllable Text Generation with Reinforced Unlearning
Large-scale language models often learn behaviors that are misaligned with user expectations. Generated text may contain offensive or toxic language, contain significant repetition, or be of a…