Mara Levy

I am a PhD student in the Computer Science department at the University of Maryland, College Park. I work on robotic learning and computer vision with Abhinav Shrivastava. I graduated Summa Cum Laude from the University of Pennsylvania where I majored in Computer Science and minored in Mathematics.

Email  /  CV  /  Scholar  /  Github

profile photo

Research

My research utilizes a mixture of computer vision and robotics approaches to try and make robots more useful in the real world. Currently I am interested in how robots can learn from a very small number of demonstrations. In the long term I am interested in using these techniques to learn from online videos of humans. These learned skills can then be combined for long term planning.

ARDuP: Active Region Video Diffusion for Universal Policies
Shuaiyi Huang, Mara Levy, Zhenyu Jiang, Anima Anandkumar, Yuke Zhua, Linxi Fan, De-An Huang, Abhinav Shrivastava
Under Submission

A novel method for learning complex goal-conditioned robotics tasks from a single demonstration, using unique reward function and knowledge expansion.

WayEx: Waypoint Exploration using a Single demonstration
Mara Levy, Nirat Saini, Abhinav Shrivastava
IEEE International Conference on Robotics and Automation (ICRA), 2024

A novel method for learning complex goal-conditioned robotics tasks from a single demonstration, using unique reward function and knowledge expansion.

Project / Paper
V-VIPE: Variational View Invariant Pose Embedding
Mara Levy, Abhinav Shrivastava
Conference on Computer Vision and Pattern Recognition (CVPR) RHOBIN Workshop, 2024

A method for projecting poses into an embedding space that is view invariant. This means the same pose shot from different camera angles should have an equal embedding.

Paper
Coarse-to-Fine Human Mesh Recovery with Transformers
Vatsal Agarwal, Mara Levy, Max Ehrlich, Youbao Tang, Ning Zhang, Abhinav Shrivastava
Under Submission

Build efficient Transformer design for non-parametric human mesh recovery with coarse-to-fine pipeline.

Paper
No-frills Dynamic Planning using Static Planners
Mara Levy, Vasista Ayyagari, Abhinav Shrivastava
IEEE International Conference on Robotics and Automation (ICRA), 2021

A planning algorithm that helps reinforcement learning algorithms that can typically only solve tasks for static objects solve the same task, but with a dynamic object.

Project / Paper

Template Credits Jon Barron