Aryan Satpathy

I completed my Bachelors from Indian Institute Of Technology, Kharagpur, majoring in Electronics and Electrical Communication Engineering. In my undergrad years, I've had the opportunity to work with Prof Amir Khajepour, Prof Duc Pham and Prof Somesh Kumar.

Currently I am working with Prof. Deepak Pathak on neuro-symbolic solver for Physics. I am also working with Prof. Saumik Bhattacharya on unsupervised arbitrary-scale pointcloud resampling. I recently collaborated with Prof. Anima Anandkumar's lab on a project in AI4Science.

Email / Github / LinkedIn / Google Scholar

Research

My broad research interests lie in advancing intelligent systems, enabling them to seamlessly process multi-modal sensor data (preferably unsupervised), and making them smarter, robust and trustworthy. More specifically, I am interested in computer vision (neural rendering, geometrical deep learning), mobile robotics (planning, world model), adversarial attacks and optimization. I also believe that we as AI researchers have the potential to make transformative contributions to scientific discovery.

Experience

University Of Waterloo
Research Intern, Guide: Prof Amir Khajepour
May - July, 2023

Worked on perception for lidar and camera for autonomous driving of robot in indoor and outdoor scenarios. Worked on multi-camera multi-object tracking and sensor fusion.

University Of Birmingham
Research Intern, Guide: Prof Duc Pham
April, 2022 - February, 2023

Worked on Bees Algorithm and its application in combinatorial optimization(GVRP). Presented our work in BAA 2022.

Indian Institute Of Technology, Kharagpur

Indian Institute Of Technology(IIT), Kharagpur
Bachelors in Electronics and Communication Eng.
Micro Specialization in Artificial Intelligence
December, 2020 - May 2024

Bachelors' Thesis: MAT-RL (Advisor: Prof Somesh Kumar)

News

[Dec 2024]

Our paper on backdoor and adversarial attacks targetting SSL was accepted at ICASSP 2025. See you at Hyderabad!

Publications

Understanding Protein-DNA Interactions by Paying Attention to Protein and Genomics Foundation Models
Dhruva Rajwade, Erica Wang, Aryan Satpathy, Alexander Brace, Hongyu Guo, Arvind Ramanathan, Shengchao Liu, Anima Anandkumar
Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges
openreview / code

Understanding DNA Protein interactions using Deep Learning.

Towards Adversarial Robustness And Backdoor Mitigation in SSL
Aryan Satpathy*, Dhruva Rajwade*, Nilaksh*, Somesh Kumar
to appear at ICASSP 2025 (* denotes equal contribution)
paper / code

Defense against backdoor attacks targetting SSL.

Bees Algorithm for Green Vehicle Routing Problem
Aryan Satpathy, Millon Madhur Das, Natalia Hartono, Duc Pham
In: Pham, D.T., Hartono, N. (eds) Intelligent Engineering Optimisation with the Bees Algorithm. Springer Series in Advanced Manufacturing. Springer, Cham.
chapter / code

Bees Algorithm for Green Vehicle Routing Problem with multiprocessing support.

Projects

	Indoor Sensor Node Perception MITACS GRI, 2023 code / documentation Multi-modal multi-object detection and tracking with overhead camera and LiDAR sensors.
	Parallel Robot Control Self Project code Implemented 6-DOF Stewart Platform and SeeSaw Environment(1-DOF approximation of Stewart Platform), in the IsaacGym framework.
	Drone Perception IMAV Indoor Challenge, 2023 code Perception stack with Lane Tracking and QR landing abilities for drones in indoor setting (without GPS reliance).
	Shader Sandbox Self Project code / video Shader implementation of Raytracing, Fog and other effects.

This webpage uses Jon Barron's template. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead.