Vaibhav Saxena
I am a Ph.D. student in Machine Learning at the Georgia Institute of Technology advised by Prof. Danfei Xu. My research revolves around generative models for decision-making, memory, and computer vision, with the goal of generalizable robot learning from offline demonstrations!
In 2019, I graduated with a Master of Science in Applied Computing from the Department of Computer Science, University of Toronto, where I was advised by Prof. Jimmy Ba and Prof. Frank Rudzicz, and worked closely with Danijar Hafner. My research involved learning state-space models for long-horizon planning, deep reinforcement learning, and multi-modal representation learning.
See more about my professional experience here.
News
[Mar 2024] We will be organizing the “Data Generation for Robotics Workshop" at RSS 2024 in Delft, Netherlands!
[Feb 2023] I will be returning to Autodesk Research as a Research Intern during Summer 2023
[Jan 2023] Our paper on "Generalizable Pose Estimation using Implicit Scene Representations" got accepted at ICRA 2023
[Dec 2022] I will be presenting our paper on "Guiding Exploration Towards Impactful Actions" at the Deep RL Workshop in NeurIPS 2022
[Feb 2022] I will be spending the Summer of 2022 as a Research Intern at Autodesk Research
[Dec 2021] I will be presenting our paper on "Clockwork Variational Autoencoders" at NeurIPS 2021 [tweet]
[Aug 2021] Joining the ML Ph.D. program at Georgia Tech!
[Apr 2021] Clockwork VAEs featured on Towards Data Science!
Research (representative works highlighted)
C3DM: Constrained-Context Conditional Diffusion Models for Imitation Learning
Query image
Pose estimation using i-σSRN
Generalizable Pose Estimation using Implicit Scene Representations
Vaibhav Saxena, Kamal Rahimi Malekshan, Linh Tran, Yotto Koga
ICRA, 2023
📄 Paper
🌐 Project Webpage
🖥️ Code
🔗 Blog
Guiding Exploration Towards Impactful Actions
Vaibhav Saxena, Jimmy Ba, Danijar Hafner
Deep Reinforcement Learning Workshop
NeurIPS, 2022
Dyna-AIL : Adversarial Imitation Learning by Planning
Vaibhav Saxena, Srinivasan Sivanandan, Pulkit Mathur
Beyond "Tabula Rasa" in Reinforcement Learning Workshop
ICLR, 2020
📄 Paper