Search Results for author:
Found 8 papers, 4 papers with code
Counterfactual World Modeling for Physical Dynamics Understanding
Third, the counterfactual modeling capability enables the design of counterfactual queries to extract vision structures similar to keypoints, optical flows, and segmentations, which are useful for dynamics understanding.
WhisBERT: Multimodal Text-Audio Language Modeling on 100M Words
Training on multiple modalities of input can augment the capabilities of a language model.
Unifying (Machine) Vision via Counterfactual World Modeling
Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets.
ENTL: Embodied Navigation Trajectory Learner
ENTL's generic architecture enables sharing of the spatio-temporal sequence encoder for multiple challenging embodied tasks.
Break and Make: Interactive Structural Understanding Using LEGO Bricks
We pair this simulator with a new dataset of fan-made LEGO creations that have been uploaded to the internet in order to provide complex scenes containing over a thousand unique brick shapes.
Interactron: Embodied Adaptive Object Detection
Our adaptive object detection model provides a 7. 2 point improvement in AP (and 12. 7 points in AP50) over DETR, a recent, high-performance object detector.
Contrasting Contrastive Self-Supervised Representation Learning Pipelines
In the past few years, we have witnessed remarkable breakthroughs in self-supervised representation learning.
AllenAct: A Framework for Embodied AI Research
The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with the advent of deep reinforcement learning and increased interest from the computer vision, NLP, and robotics communities.
