About Me
Hi! I am a second year Master's student at the Robotics Institute, Carnegie Mellon University working with Prof. Deepak Pathak. Prior to joining CMU, I was a deep learning research engineer at Preimage with a super amazing team building cutting-edge 3D reconstruction and drone photogrammetry platform.
Before that, I also worked as a visiting researcher at the Cognitive Learning and Vision for Robotics (CLVR) Lab at University of Southern California (USC), USA under the guidance of Dr. Joseph Lim.
I also briefly worked at the Deep cognition and Language Research (DeCLaRe) Lab at Singapore University of Technology and Design (SUTD) working on vision and language applications.
Previously, I interned at BRAIN Lab, SUTD working on the unsupervised disentangled representation learning for video sequences.
During my Bachelors, I worked with Dr. Saket Anand in the Infosys Centre of Artificial Intelligence and Dr. Pavan Turaga on unsupervised representation learning for disentangling multiple factors of variation in images and analysing the geometry of their latent spaces. I also worked with Dr. Rajiv Ratn Shah and Vivek Gupta (currently pursuing PhD, School of Computing, University of Utah) on Natural Language Inference for low-resource languages.
Apart from my research interests, I love playing Badminton, spending time with colors, poetry, star gazing, and reading about Astronomy ( I am an astrophile! :) ).
Interests
- Representation Learning
- Disentanglement
- Self supervised Learning
- Computer Vision
- Robotics
- Artificial Intelligence
Education
-
Master's in Robotics, 2022-2024
Carnegie Mellon University, USA
-
B.Tech in Computer Science and Engineering (with Honors), 2016-2020
IIIT Delhi, India
News
November, 2023: Attending CoRL 2023, Atlanta.
August, 2022: Joined Carnegie Mellon University for MS in Robotics
July, 2022: Received the prestigious J.N. Tata Scholarship for higher education
December, 2021: Volunteered at NeurIPS
September, 2021: One paper accepted at CoRL 2021
December, 2020: Volunteered at NeurIPS
August, 2020: Presented work on Disentangling Video Sequences using Gaussian Processes at ECCV
July, 2020: Code released for MGP-VAE
July, 2020: Presented work on Self-supervised disentanglement using Contrastive Learning at ICML Workshop
July, 2020: Volunteered at ICML
May, 2020: Joined LinkedIn AI Team for summer internship
May, 2019: Visiting student at Brain Lab, Singapore University of Technology and Design (SUTD)
May, 2019: Attended Google I/O in Mountain View, California
Publications
* indicates equal contribution.
Conference Papers
Dextrous Functional Grasping
Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation
Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders
PrOSe: Product of Orthogonal Spheres Parameterization for Disentangled Representation Learning
DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors
C3VQG: Category Consistent Cyclic Visual Question Generation
Geometry of Deep Generative Models for Disentangled Representations
Journal Papers
Multimodal Research in Vision and Language: A Review of Current and Emerging Trends
Teaching
Deep Learning (CSE641)
Graduate Level CourseCourse offered by Dr. Saket Anand in Spring 2020
Machine Learning (CSE543)
Graduate Level Course Course offered by Dr. Saket Anand in Fall 2019Contact
Please feel free to reach to me for any query or interesting collaborations.
- shagunu [at] andrew [dot] cmu [dot] edu