Hi, I’m Aryan Goyal.
I recently graduated from the Indian Institute of Technology Bombay.
I’m an incoming MS in Computer Vision student at the Robotics Institute, School of Computer Science, Carnegie Mellon University.
I work on imitation learning, with a generalist robot policy as the north star.
Previously, I worked on fine-grained medical imaging at Qure.AI.
Research Interests
“What are the most important problems in your field? And why aren’t you working on them?” — Richard Hamming
In December 2025, I changed the way I choose research problems. I grew more interested in fundamental questions than in specific heuristics — problems where the path forward is unclear and hard, but where progress would meaningfully move the field. My approach is to hold a hard, general problem as a north star and design pragmatic proxy experiments around it, with the constraint that success on those experiments should translate to real progress on the larger problem.
I’m especially excited about the physical-intelligence space — it’s remarkable to see robotics finally starting to work, though there is a long way to go. I am currently working on the long-horizon task problem.
Publications
Measuring the Stability Assumption Behind Action Chunking
arXiv preprint, 2026 · arXiv · Project pageThe Hitchhiker’s Guide to Mechanistic Interpretability of Vision-Language-Action Models
Mechanistic Interpretability Workshop at ICML, 2026 · Paper · Project pageA Diffusion-Driven Fine-Grained Nodule Synthesis Framework for Enhanced Lung Nodule Detection from Chest Radiographs
Medical Imaging with Deep Learning (MIDL), 2026 · arXiv · Project pageDiffusionXRay: A Diffusion and GAN-Based Approach for Enhancing Digitally Reconstructed Chest Radiographs
DEMI Workshop at MICCAI, 2025 · arXiv · Project pageACADEMIA: Curriculum-Aligned Multi-Agent Orchestration for K-12 Education
Preprint, 2026
Patents
- A System and Method for Projecting Synthetic Nodules in Medical Imaging
Indian Patent Application No. 202521024259
Apart from work
I spend my time playing tennis, I like to grab a cold one with my friends and I make amazing hot pour-overs. I listen to all genres of music, I love listening to new music and making playlists for my friends.
