AI2-THOR: An Interactive 3D Environment for Visual AI
- Eric Kolve, Roozbeh Mottaghi, Ali Farhadi
- Computer ScienceArXiv
- 14 December 2017
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
- Matt Deitke, Winson Han, Ali Farhadi
- Computer ScienceComputer Vision and Pattern Recognition
- 14 April 2020
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
- Sarah Pratt, Mark Yatskar, Luca Weihs, Ali Farhadi, Aniruddha Kembhavi
- Computer ScienceEuropean Conference on Computer Vision
- 26 March 2020
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%.
Simple but Effective: CLIP Embeddings for Embodied AI
- Apoorv Khandelwal, Luca Weihs, Roozbeh Mottaghi, Aniruddha Kembhavi
- Computer ScienceComputer Vision and Pattern Recognition
- 18 November 2021
One of the baselines is extended, producing an agent capable of zero-shot object navigation that can navigate to objects that were not used as targets during training, and it beats the winners of the 2021 Habitat ObjectNav Challenge, which employ auxiliary tasks, depth maps, and human demonstrations, and those of the 2019 Habitat PointNav Challenge.
Visual Room Rearrangement
- Luca Weihs, Matt Deitke, Aniruddha Kembhavi, Roozbeh Mottaghi
- Computer ScienceComputer Vision and Pattern Recognition
- 30 March 2021
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.
Learning to Predict Citation-Based Impact Measures
- Luca Weihs, Oren Etzioni
- Computer ScienceACM/IEEE Joint Conference on Digital Libraries
- 1 June 2017
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.
Gender trends in computer science authorship
- Lucy Lu Wang, Gabriel Stanovsky, Luca Weihs, Oren Etzioni
- ArtCommunications of the ACM
- 19 June 2019
Under optimistic projection models, gender parity is forecast to be reached after 2100.
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
- Unnat Jain, Luca Weihs, A. Schwing
- Computer ScienceEuropean Conference on Computer Vision
- 9 July 2020
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.
Determinantal Generalizations of Instrumental Variables
- Luca Weihs, B. Robinson, M. Drton
- Mathematics
- 13 February 2017
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…
AllenAct: A Framework for Embodied AI Research
- Luca Weihs, Jordi Salvador, Aniruddha Kembhavi
- Computer ScienceArXiv
- 28 August 2020
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.
...
...