RECAST: Reconstruction-Anchored Semi-Supervised Training for Low-Resource Machine Translation
Bathla, D., Singla, P., & Singla, J.
Submitted to AAAI-27
Singla Lab · Biosciences & Bioengineering
We look for structure —
in cells and signals.
The Singla Lab at IIT Roorkee builds computational frameworks that bridge biology, data science and engineering — cellular architecture from tomography, AI for healthcare diagnostics, and Sanskrit language models.
26
Publications
7
Doctoral researchers
60
Alumni & interns
12
Sponsored projects
“Story telling is essentially a data integration process.”
Jitin Singla
What we work on
Three threads, one question: how do you get from raw measurement to something you can reason about?
01
Cellular architecture
Mitochondrial network modelling with soft X-ray tomography
Soft X-ray tomography (SXT) rapidly maps ultrastructure across whole, intact cells. We build the tools that turn those volumes into measurable biology.
02
AI for healthcare
Non-invasive diagnostics from images and signals
Jaundice affects 60–80% of newborns worldwide. A phone camera should be enough to triage it.
03
Low-resource NLP
AI models for Sanskrit
Sanskrit is morphologically rich and data-poor — exactly the regime where modern NLP is weakest.
Principal Investigator
Jitin Singla, PhD
Assistant Professor · Department of Biosciences and Bioengineering, IIT Roorkee
I am an Assistant Professor in the Department of Biosciences and Bioengineering at IIT Roorkee. My research group develops computational frameworks that bridge biology, data science and engineering — specifically, problems in computational biology and AI-driven bioimage analysis for healthcare diagnostics. More recently we have begun an adventure into Sanskrit-AI tools.
Our current projects span computational characterization of cellular architecture, AI-based jaundice detection, ECG analysis, and AI models for Sanskrit.
Education
- PhD, Computational Biology & BioinformaticsUniversity of Southern California
- M.S., Computer Science (HPC & Simulation)University of Southern California
- B.Tech., Computer Science & EngineeringIIT Roorkee
Recent work
Selected publications
FiRe: Frequency Reparameterization as a Preconditioner for Periodic Implicit Neural Representations
Shukla, H., Verma, R., & Singla, J.
arXiv preprint, arXiv:2606.29414
Singh, A., Yadav, A., Deshmukh, A., Singh, A., Verma, R., White, K., & Singla, J.
Structure, Accepted
Pathology-Aware Multi-View Contrastive Learning for Patient-Independent ECG Reconstruction
Youssef, Y., & Singla, J.
arXiv preprint, arXiv:2603.17248
Samasamayik: A Parallel Dataset for Hindi–Sanskrit Machine Translation
Karthika, N. J., Suryanarayanan, K., Purohit, J., Ramakrishnan, G., Singla, J., & Gourishetty, A. K.
arXiv preprint, arXiv:2603.24307
Lab notes
Latest news
2026
Two papers accepted in Structure and Journal of Structural Biology
Morphotype-resolved 3D morphometry of mitochondrial networks accepted in Structure, and robust mitochondria segmentation with soft X-ray tomography published in the Journal of Structural Biology.
March 2026
Divyanshu Bathla awarded the IndiaAI PhD Fellowship
Divyanshu Bathla, a doctoral student in the lab, has received the IndiaAI PhD Fellowship for his work building Sanskrit-AI tools. A national initiative under the IndiaAI Mission, it supports full-time doctoral researchers in AI with a monthly stipend of ₹70,000–80,000, an annual research grant of ₹2 lakh, and conference travel support of up to ₹1 lakh.
6 December 2025
Interaction with participants at MMTTC, HNB Garhwal University
Prof. Parikshit Pareek and Jitin Singla engaged with attendees at MMTTC as part of a Faculty Development Programme on “Harnessing AI in Higher Education for an Innovative Future”.
Collaborating with
- IIT Roorkee
- PGIMER Chandigarh
- IIT Delhi
- UCLA
- University of Southern California
- Rutgers University
- UCSF
Work with us
We look for people who want to build, question and grow — not collect credentials.