I leverage Theoretical Physics + Computational Statistics to mathematically model Artificial
Intelligence -- focusing particularly on Mechanistic Interepretability (MI), Uncertainty Quantification
(UQ), and Safety. Additionally, I wear a Physicist hat, wherein, I apply AI to model and simulate Quantum, across
the domains of Theoretical Particle Physics and Quantum Matter. You can see my publication list at
Google Scholar.
I am actively looking for motivated PhD, Masters and senior Undegrad students to join my group.
Please feel free to reach out if my work resonates with you.
Biography
Geographically, my academic journey resembles a rectangle.
Prior to joining IIT Kharagpur,
I was a postdoctoral research fellow at Perimeter Institute for
Theoretical Physics, jointly with
PIQuIL, from Sept 2023 till Aug 2026. During this time, I have been fortunate to be
mentored by Prof. Roger Melko, while I explored
Physics of AI: Scaling Laws, Mechanistic Interpretability, Uncertainty Quantification; and constructed theory-driven
Generative AI frameworks for Quantum Field Theory and Quantum Many-Body Physics.
Prior to this, I was a postdoctoral research fellow in the Pehlevan Group
at Harvard University, Dept. of Applied Math (SEAS),
from May 2023 through Aug 2023. I have been fortunate to be mentored
by Prof. Cengiz Pehlevan during this period and beyond, as I expanded
my horizons into Theory of Deep Learning, especially via Applied Math and Computational Statistics.
I completed my PhD on AI for Effective Field Theory at Northeastern University, Boston,
in Apr 2023 -- as one of the founding co-authors of the domain Neural
Network Field Theory correspondence. I am fortunate to have been guided by Prof.
Jim Halverson during my PhD. I was also a junior investigator at the NSF IAIFI,
from Oct 2020 till Aug 2023. .
My research and publication details can be found on other tabs.
Curriculum Vitae
Research
Details to be refreshed.
Teaching
As a faculty in IIT Kharagpur.
Fall 2026 (post mid-semester exam):Linear Algebra for AI (AI21203) for sophomores.
As a Postdoctoral Fellow at Perimeter & Harvard.
Future Horizons: Bridging AI, Quantum and New Materials 2024 Workshop: Lecture and tutorial on
Machine Learning from a Physicist’s Perspective
The NSF IAIFI Summer School 2023: Tutorial Lead on
'Normalizing Flows for Lattice Field Theory' lectures by Miranda Cheng
People
To be added.
Contact
amaiti@ai.iitkgp.ac.in
Dept. of Artificial Intelligence, CRR Floor-6 Office #4, Indian Institute of Technology Kharagpur, India 721302.
Elements
Text
This is bold and this is strong. This is italic and this is emphasized.
This is superscript text and this is subscript text.
This is underlined and this is code: for (;;) { ... }. Finally, this is a link.
Heading Level 2
Heading Level 3
Heading Level 4
Heading Level 5
Heading Level 6
Blockquote
Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.
Preformatted
i = 0;
while (!deck.isInOrder()) {
print 'Iteration ' + i;
deck.shuffle();
i++;
}
print 'It took ' + i + ' iterations to sort the deck.';