is a group of researchers who study, analyze, and build various aspects of AI (including social) systems. Our work spans several areas - Applied Machine Learning, Responsible and Safe AI, Natural Language Processing, and Social Network Analysis. By understanding and measuring AI systems, we aim to develop solutions that contribute to the greater good of society.
Latest News
Dec 2024
Huge congratulations to Varshita Kolipaka (9th Semester Dual Degree IIITH), for winning the 5th position at the poster session at IndoML!
Dec 2024
Attending IndoML2024 in Goa (Dec 21–23)? Meet Vamshi Krishna Bonagiri & Varshita Kolipaka, two BTech + MS Dual Degree students from Precog-at-IIITH.
Dec 2024
Paper "Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting" accepted at COLING 2025.
See More
Higher Order Structures For Graph Explanations
Akshit
Sinha* , Sreeram
Vennam* , Charu
Sharma, and Ponnurangam
Kumaraguru
In The 39th Annual AAAI Conference on Artificial Intelligence , 2025
@inproceedings { sinha2024higherorderstructuresgraph ,
title = {Higher Order Structures For Graph Explanations} ,
author = {Sinha, Akshit and Vennam, Sreeram and Sharma, Charu and Kumaraguru, Ponnurangam} ,
year = {2025} ,
eprint = {2406.03253} ,
archiveprefix = {arXiv} ,
primaryclass = {cs.LG} ,
booktitle = {The 39th Annual AAAI Conference on Artificial Intelligence} ,
}
Corrective Machine Unlearning
Shashwat
Goel, Ameya
Prabhu, Philip
Torr, Ponnurangam
Kumaraguru, and Amartya
Sanyal
Transactions on Machine Learning Research , 2024
@article { goel2024corrective ,
title = {Corrective Machine Unlearning} ,
author = {Goel, Shashwat and Prabhu, Ameya and Torr, Philip and Kumaraguru, Ponnurangam and Sanyal, Amartya} ,
journal = {Transactions on Machine Learning Research} ,
issn = {2835-8856} ,
year = {2024} ,
}
Random Representations Outperform Online Continually Learned Representations
Ameya
Prabhu, Shiven
Sinha, Ponnurangam
Kumaraguru, Philip
Torr, Ozan
Sener, and Puneet K.
Dokania
In The Thirty-eighth Annual Conference on Neural Information Processing Systems , 2024
@inproceedings { prabhu2024random ,
title = {Random Representations Outperform Online Continually Learned Representations} ,
author = {Prabhu, Ameya and Sinha, Shiven and Kumaraguru, Ponnurangam and Torr, Philip and Sener, Ozan and Dokania, Puneet K.} ,
booktitle = {The Thirty-eighth Annual Conference on Neural Information Processing Systems} ,
year = {2024} ,
url = {https://openreview.net/forum?id=TZ5k9IYBBf} ,
}
Representation Surgery: Theory and Practice of Affine Steering
Shashwat
Singh, Shauli
Ravfogel, Jonathan
Herzig, Roee
Aharoni, Ryan
Cotterell, and Ponnurangam
Kumaraguru
In Forty-first International Conference on Machine Learning , 2024
@inproceedings { singhrepresentation ,
title = {Representation Surgery: Theory and Practice of Affine Steering} ,
author = {Singh, Shashwat and Ravfogel, Shauli and Herzig, Jonathan and Aharoni, Roee and Cotterell, Ryan and Kumaraguru, Ponnurangam} ,
booktitle = {Forty-first International Conference on Machine Learning} ,
year = {2024} ,
}
Thank you for your interest in joining our team! We are always looking for talented and motivated individuals to join our team. If you are interested in working with us, please
apply here .