• Publications
  • Influence
AI2-THOR: An Interactive 3D Environment for Visual AI
TLDR
AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks and facilitate building visually intelligent models.
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
TLDR
RoboTHOR offers a framework of simulated environments paired with physical counterparts to systematically explore and overcome the challenges of simulation-to-real transfer, and a platform where researchers across the globe can remotely test their embodied models in the physical world.
Grounded Situation Recognition
TLDR
A Joint Situation Localizer is proposed and it is found that jointly predicting situations and groundings with end-to-end training handily outperforms independent training on the entire grounding metric suite with relative gains between 8% and 32%.
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
TLDR
The novel task FurnMove is introduced, in which agents work together to move a piece of furniture through a living room to a goal, and SYNC-policies (synchronize your actions coherently) and CORDIAL (coordination loss) are introduced.
Visual Room Rearrangement
TLDR
The experiments show that solving this challenging interactive task that involves navigation and object interaction is beyond the capabilities of the current state-of-the-art techniques for embodied tasks and the authors are still very far from achieving perfect performance on these types of tasks.
Determinantal Generalizations of Instrumental Variables
Abstract Linear structural equation models relate the components of a random vector using linear interdependencies and Gaussian noise. Each such model can be naturally associated with a mixed graph
Learning to Predict Citation-Based Impact Measures
TLDR
This work finds that existing probabilistic models for paper citations can predict measures of scientific impact for papers and authors, namely citation rates and h-indices, with surprising accuracy, even 10 years into the future.
Efficient computation of the Bergsma–Dassios sign covariance
TLDR
An algorithm is derived that computes a covariance measure for two ordinal random variables that vanishes if and only if the two variables are independent using only On2log(n) operations.
Learning to predict citation-based impact measures
TLDR
This work finds that existing probabilistic models for paper citations can predict measures of scientific impact for papers and authors, namely citation rates and h-indices, with surprising accuracy, even 10 years into the future.
AllenAct: A Framework for Embodied AI Research
TLDR
AllenAct is introduced, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research that provides first-class support for a growing collection of embodied environments, tasks and algorithms.
...
1
2
3
...