Rishab Balasubramanian

I am currently a first year PhD student at Virginia Tech, advised by Tu Vu. My research interests lie at the intersection of multimodal deep learning, efficiency and alignment. This includes data selection for pre-training, grounded representation learning, mechanistic interpretability, sparsity, model merging and distillation, and better model architectures. Previously, I worked with Huazheng Wang on adversarial attacks on bandit algorithms and the impact of ordering in recommendation systems. Before that I was a Data Scientist/Computer Vision Engineer at EndovisionAI. Here I worked on SLAM and Shape from Shading methods for reconstructing human anatomy using endoscope images. I was also a Research Assistant at MARMoT Laboratory, and the MOON Laboratory. I completed my Bachelor's (B.Tech) from the National Institute of Technology Tiruchirapalli (NIT-Trichy), India, where I was a part of RMI, the robotics club.

In my spare time, I enjoy the adrenaline of competition from playing video games (such as Dota 2, Rainbow Six Siege and Valorant) and competitive programming. I also contribute to open source (huggingface, pytorch lightning).

Email  /  CV  /  Github  /  Google Scholar

Working on autonomous control of a legged robot to map a room using RTABMap Framework

Multi agent collision Avoidance using the Optimal Reciprocal Collision Avoidance (ORCA) Algorithm and comparison with other algorithms

Simulated a dynamic ball-balancing robot, with point to point movement using a PID controller

Special thanks to Jon Barron for the website template