Shamit Lal

I am an Applied Scientist at AWS AI Labs, Amazon. I work on generative AI and vision language models.
Previously, I worked as a researcher at Fyusion, where I worked on problems related to 6DOF pose estimation, object detection and segmentation, and distillation of large models.
Even before that, I completed my masters in computer vision (MSCV) at Carnegie Mellon University advised by Professor Katerina Fragkiadaki.


News


Mar 2021
CoCoNets accepted at CVPR 2021
Jan 2021
2 papers (Disentangling 3D Prototypical Networks and HyperDynamics) accepted at ICLR 2021
Oct 2020
3D-OES accepted at CoRL 2020
Oct 2020
Disentangling 3D Prototypical Networks paper accepted as at NeurIPS ORLR workshop 2020 (oral).
May 2020
3DQ-Nets accepted at CVPR workshop 2020.
Aug 2019
Started my masters program at Carnegie Mellon University.
Mar 2019
Promoted to SDE-2 at Amazon.
Nov 2018
Online Video Summarization accepted at WACV 2019.
Oct 2017
Our paper Image Colorization Using Adversarial Training got accepted at ICSPS 2017.
Aug 2017
Graduated from DTU, joining Amazon India as SDE-1.
Dec 2016
ACM ICPC India Finalist (National Rank 28).

Publications and Pre-Prints


CoCoNets: Continuous Contrastive 3D Scene Representations
Shamit Lal*, Mihir Prabhudesai*, Ishita Mediratta, Adam W Harley, Katerina Fragkiadaki (* = Equal Contribution)
CVPR 2021
Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
Mihir Prabhudesai*, Shamit Lal*, Darshan Patil*, Hsiao-Yu Tung, Adam W Harley, Katerina Fragkiadaki (* = Equal Contribution)
ICLR 2021 | Neurips 2020 ORLR Workshop (Oral)
HyperDynamics: Meta-learning object and agent dynamics with hypernetworks
Zhou Xian, Shamit Lal, Hsiao-Yu Fish Tung, Emmanouil Antonios Platanios, Katerina Fragkiadaki
ICLR 2021
3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators
Hsiao-Yu Fish Tung*, Zhou Xian*, Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki (* = Equal Contribution)
CoRL 2020
3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
Mihir Prabhudesai*, Shamit Lal*, Hsiao-Yu Fish Tung, Adam W. Harley, Shubhankar Potdar, Katerina Fragkiadaki (* = Equal Contribution)
Arxiv (full paper in submission) | CVPR Workshop 2020
Online Video Summarization: Predicting Future to Better Summarize Present
Shamit Lal*, Shivam Duggal*, Indu Sreedevi (* = Equal Contribution)
WACV 2019
Automatic image colorization using adversarial training
Shamit Lal, Vineet Garg, O.P.Verma
ICSPS 2017