|
Eric Zhu I am a masters student in robotics at Carnegie Mellon where I research the intersection of machine learning, reinforcement learning, robotics, and autonomous vehicles. I am fortunate enough to be advised by Jeff Schneider. Previously, I was an undergraduate at the University of Maryland, College Park, where I double majored in Computer Science and Mathematics. During the course of my undergrad, I worked with Abhinav Shrivastava in machine learning, computer vision and robotics. |
|
ResearchI'm interested in computer vision, generative AI, robotics, and 3D world models. My current research focuses on integrating novel view synthesis networks into robotic algorithms. |
|
NeRF-Aug: Data Augmentation for Robotics with Neural Radiance Fields
Eric Zhu, Mara Levy, Matthew Gwilliam, Abhinav Shrivastava Accepted into CoRL 2025 Rational Robotics Workshop and CoRL2025 Robot Data Workshop (Spotlight, top 4 submissions) A novel method that is capable of teaching a policy to interact with objects that are not present in the dataset through the use of NERF based scene augmentation. Paper / arXiv / Project Page |
|
Hindsight Experience Replay in the Visual Domain
With Novel View Synthesis Networks
Eric Zhu, Mara Levy, Abhinav Shrivastava Undergraduate Honors Thesis A method that leverages NeRF models to effectively bring a reinforcement learning algorithm called hindsight experience replay into the visual domain. Paper |
|
Maternal depressive symptoms, attendance of sessions and reduction of home safety problems in a randomized toddler safety promotion intervention trial: A latent class analysis
Yan Wang, Eric Zhu, Erin Hager, Maureen Black Accepted into PLOS ONE An analysis linking maternal depression, attendance of toddler safety promotion sessions, and todler safety using Latent Class Analysis. Paper |
|
Feel free to steal this website's source code. Do not scrape this page's HTML as it contains analytics tags. |