Anshuman Sinha

Hello! My name is Anshuman, I'm a MS CSE student from Georgia Tech, working at the intersection of Machine Learning and Science. I am interested in developing bayesian learning architectures with physics-based priors for natural science applications.

I am currently working at the Fung Group with Prof. Victor Fung with a focus on Deep Generative Models for scientific discovery. Along with that I am working on Multi-modal Language models. I am interested in the intersection of Genretaive AI and Science

Prior to joining Getech, I did my BTech from IIT Kanpur (India) in the field of Materials Science and Computation (Proficiency Gold Medal).

My general interest hovers around topics in the field of Generative AI , LLMs and Latent variable models with applications in Natural sciences and Social good. Kindly reach out to me for more details. On a side note, If you are interested in joining me towards educating underprivileged children, please contact me.

Recent Research

Generative Diffusion model for structure representation

Anshuman Sinha, Shuyi Jia, Victor Fung,

Under open-review

ICLR 2024 (prospective)

Soon   |   Paper   |   Project page   |   Code   |  

Multi-modal LLMs: Instilling time through post-pretraining

Anshuman Sinha, Aubin Rey, Camille Migozzi,

Under open-review

ICML 2024 (prospective)

Soon   |   Paper   |   Project page   |   Code   |  

Generative AI: Calorimer design SSL

LLNL and LBNL authouths/u>,

In draft

Internship projects

ArXiv   |   Paper   |   Project page   |   Code   |  

SSL: Graph SSL

Anshuman Sinha, Bhavay Aggrawal

MLC 2023

Course project on Self-supervised graph learning

Submission   |   Code   |   PPT  

Vision generative model: Images DDPM

Anshuman Sinha (Reproducibility)

from lucidrain

Lucid rain's implementation for my research

Code   |   PPT (⌛)