Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

What do navigation agents learn about their environment?

Kshitij DwivediG. RoigAniruddha KembhaviRoozbeh Mottaghi
2022
arXiv

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

Jiasen LuChristopher ClarkRowan ZellersAniruddha Kembhavi
2022
arXiv

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

Gregor BetzKyle Richardson
2022
SEM

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

Spencer K. ClarkNoah D. BrenowitzBrian HennLucas M. Harris
2022
Earth and Space Science Open Archive

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

Sheshera MysoreArman CohanTom Hope
2022
NAACL

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

Dustin SchwenkApoorv KhandelwalChristopher ClarkRoozbeh Mottaghi
2022
arXiv

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

Zejiang ShenKyle LoLucy Lu WangDoug Downey
2022
TACL

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?

Teven Le ScaoThomas WangDaniel HesslowIz Beltagy
2022
EMNLP

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

James FergusonPradeep DasigiTushar KhotHannaneh Hajishirzi
2022
ACL • FEVER

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

Ximing LuS. WelleckLiwei JiangYejin Choi
2022
NeurIPS

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…