Devichand Budagam

These days I’m more interested in understanding evolution and intelligence. I’m curious about how we can design representations, parameter collections, objectives and training/testing curricula to create models that are as sample efficient and adaptable as humans or better than us and evolve continuously to ever-changing data environments.

My research boradly touches areas like evolutionary computation, sample efficiency, meta-learning, continual learning, information theory, and interpretability. I also draw on physics, cognitive science, and cellular biology. I see these fields as essential for understanding intelligence, and the world it inhabits.

If you want to evolve in a tiny new world, far simpler than human lives, you can go here!!

I had completed my Dual Degree (B.Tech + M.Tech) in Computer Science and Engineering from IIT Kharagpur under the supervision of Dr. Pawan Goyal and Dr. Manish Gupta.

Feel free to reach out at devichand579[at]gmail[dot]com if you have questions, want to discuss research, or are interested in collaborating.

selected publications

EACL

Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs

Sandeep Mishra, Devichand Budagam, Anubhab Mandal, Bishal Santra, Pawan Goyal, and 1 more author

In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track), Mar 2026

DOI arXiv Bib HTML PDF Code

@inproceedings{mishra-etal-2026-router,
  title = {Router-Suggest: Dynamic Routing for Multimodal Auto-Completion in Visually-Grounded Dialogs},
  author = {Mishra, Sandeep and Budagam, Devichand and Mandal, Anubhab and Santra, Bishal and Goyal, Pawan and Gupta, Manish},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track)},
  year = {2026},
  month = mar,
  address = {Rabat, Morocco},
  publisher = {Association for Computational Linguistics},
  pages = {145--156},
  doi = {10.18653/v1/2026.eacl-industry.11},
  url = {https://aclanthology.org/2026.eacl-industry.11/},
}

KDD workshop

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles

Devichand Budagam, Ashutosh Kumar, Mahsa Khoshnoodi, Sankalp KJ, Vinija Jain, and 1 more author

Aug 2025

arXiv Bib HTML PDF Code

@misc{budagam2025hierarchicalpromptingtaxonomyuniversal,
  title = {Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles},
  author = {Budagam, Devichand and Kumar, Ashutosh and Khoshnoodi, Mahsa and KJ, Sankalp and Jain, Vinija and Chadha, Aman},
  year = {2025},
  month = aug,
  booktitle = {KDD 2025 Workshop on Prompt Optimization},
  journal = {arXiv preprint arXiv:2406.12644},
  eprint = {2406.12644},
  archiveprefix = {arXiv},
  primaryclass = {cs.CL},
  url = {https://arxiv.org/abs/2406.12644},
}

news

Jul 22, 2026	Started as Artificial Intelligence Engineer 2 at KLA Corporation.
Jun 24, 2026	Selected among the top 1% of startups for the Off Season II accelerator at Founders, Inc.
Jun 22, 2026	Received the AMD GPU Open Research Grant for my master’s thesis with Dr. Pawan Goyal.
Jan 05, 2026	Paper accepted as an oral at EACL 2026 Industry Track.
Aug 04, 2025	Paper accepted to KDD 2025 Workshop on Prompt Optimization.