
Harsha Nelaturu
I work on developing efficient training and inference methods for large-scale deep learning systems. My research leverages compression techniques such as sparsification, quantization, and distillation to build computationally and memory-efficient models. In addition, I am also interested in robust model evaluation and trustworthiness.
📬 Contact
- office
- Room 3027 at ZIB
- nelaturu (at) zib.de
- languages
- English, Telugu, and Hindi
🎓 Curriculum vitae
- since 2025
- Researcher at ZIB
📝 Publications and preprints
Preprints
- Batzner, J., Nelaturu, H., Stachura, D., Kornilova, A., Crall, J., Cerruti, T., Long, Y., Mai, Y., Ahuja, S., Yehudai, A., Šuppa, M., Lalor, J. P., Olowe, O., Ganhotra, J., Hu, B. H., Habba, E., Bean, A. M., Liu, C., Land, S., … Choshen, L. (2026). Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results.
[arXiv]
[BibTeX]
@misc{2026_BatznerEtAl_EvalSchemaRepository_2606-14516, archiveprefix = {arXiv}, eprint = {2606.14516}, arxiv = {arXiv:2606.14516}, primaryclass = {cs.AI}, year = {2026}, author = {Batzner, Jan and Nelaturu, Harsha and Stachura, Damian and Kornilova, Anastassia and Crall, Jon and Cerruti, Tommaso and Long, Yanan and Mai, Yifan and Ahuja, Sanchit and Yehudai, Asaf and Šuppa, Marek and Lalor, John P. and Olowe, Oluwagbemike and Ganhotra, Jatin and Hu, Brian H. and Habba, Eliya and Bean, Andrew M. and Liu, Chang and Land, Sander and Dillmann, Steven and Garikaparthi, Aniketh and Bandel, Elron and Imai, Saki and Edgell, James and Kennedy, Wm. Matthew and Chim, Jenny and Meusling, Patrick and Kaeberlein, Asteria and Chundi, Venkata Ramachandra Karthik and Patwardhan, Manasi and Ku, Martin and Meek, Austin and Knauer, Leon and Wingenroth, Brian and Yadav, Srishti and Gohar, Usman and Friedrich, Felix and Lin, Michelle and Mickel, Jennifer and Cohan, Arman and Biderman, Stella and Solaiman, Irene and Talat, Zeerak and Reuel, Anka and Akhtar, Mubashara and Kasneci, Gjergji and Ghosh, Avijit and Choshen, Leshem}, title = {Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results}, date = {2026-06-12} } - Nelaturu, H., Ravichandran, N. K., Tran, C., Hooker, S., and Fioretto, F. (2023). On The Fairness Impacts of Hardware Selection in Machine Learning.
[arXiv]
[BibTeX]
@misc{2023_NelaturuEtAl_HardwareSelectionFairness_2312-03886, archiveprefix = {arXiv}, eprint = {2312.03886}, arxiv = {arXiv:2312.03886}, primaryclass = {cs.LG}, year = {2023}, author = {Nelaturu, Harsha and Ravichandran, Nishaanth Kanna and Tran, Cuong and Hooker, Sara and Fioretto, Ferdinando}, title = {On The Fairness Impacts of Hardware Selection in Machine Learning}, date = {2023-12-06} }