I'm a 1st year PhD student at Mila and Université de Montréal advised by Prof. Pierre-Luc Bacon. My research interests are generative models + reinforcement learning. Currently, I focus on reward alignment and building adaptive agents for test-time generalization. My research is supported by the FRQNT doctoral scholarship.
Kinematic aware, animatable, and class-agnostic 3D deformable objects from casual monocular videos without the use of any priors or camera poses - A Template-Free Approach
Projects and Competitions
*Below are some of the projects I had fun working on, click the title for details.
Diffusion Policy Gradient - Racing with Diffusion!
Learning racing behaviors from scratch! We adopt DIPO with some adaptations for exploration, enabling it to learn in a model-free and online RL fashion.
Our experiments on zero-shot results on unseen racetracks, with higher speeds and more agents, demonstrate that only the diffusion policy gradient approach succeeds,
while classical approaches like PPO, SAC, and TD3 fail.
3D Vision Based Grasp Planning for Transparent Objects - Grasping with NeRFs!
Learning to grasp transparent objects using NeRFs and depth-aware grasping. We propose a novel approach to learn the depth map of transparent objects and use it to plan grasps.
Motion prediction with rasterized images using CNN and LSTM encoder-decoder models. Also exploring Kalman filters and other optimization techniques to enhance non-learning-based approaches. Currently working on Vectornet for a faster, raster-free pipeline.
Detection of helmets, player classification, tracking using Kalman and DeepSORT for accurate mapping. Implemented predictive tracking and analysis of game trends using past data.
• Designed a slider-crank actuation mechanism to automate compression in BVM ventilators.
• Conducted pressure trajectory analysis using COMSOL multiphysics to achieve required PIP and PEEP values at the outlet.
• Fabricated and characterized a device utilizing MOF as advanced moisture sorbents for energy-efficient high-temperature cooling.
• Conducted XRD and Thermogravimetric Analysis to assess MOF structure and water uptake characteristics.
More Projects
G2Net Gravitational Wave Detection - European Gravitational Observatory: Find gravitational wave signals from binary black hole collisions Used FFT and 1D CNN to detect the gravitational waves.
Placed 33/1219 teams
March Machine Learning Mania 2022 - Men’s: Predict the 2022 College Men's Basketball Tournament (kaggle competition), also here is the visulalization tool for bracket builing
NCAA_BracketBuilder Placed 14/930 participants
Crypto- Market prediction based on anonymised features (Ubiquant Market Prediction) I
Used Tabnet based model.
Placed 99/2893 participants
TEAM YUKTA RACING - Autobots Assemble! We Build, We Race.....! Defending Champions of GKDC 2020
