Research Interests
My general interests are all things Deep Learning, Natural Language Processing, and Reinforcement Learning. I am interested in building models that are efficient, can generalize better, and adapt to new scenarios through a higher level understanding of their environment. Currently I am working on efficient domain adaptation of LLMs.
In the application side, I am interested in a broad range of domains including Computational Social Science, Multimodal Learning, and Privacy Preserving Deep Learning. I have been fortunate to contribute to a wide range of research directions, and my work in these areas has been published at venues such as ACL, AISTATS, EMNLP, and ACM SIGIR.
|
Publications
* indicates joint first authors
|
|
Learning Through Interpolative Augmentation of Dynamic Curvature Spaces
Parth Chhabra*,
Atula Tejaswi*
Shivam Agarwal,
Ramit Sawhney,
Megh Thakkar,
Preslav Nakov,
Sudheer Chava
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2023)
Paper
|
|
How Much User Context Do We Need? Privacy by Design in Mental Health NLP Applications
Ramit Sawhney*,
Atula Tejaswi*
Ivan Habernal,
Lucie Flek
The International AAAI Conference on Web and Social Media (ICWSM 2023)
Paper
|
|
Tweet Based Reach Aware Temporal Attention Network for NFT Valuation
Ramit Sawhney,
Megh Thakkar,
Ritesh Soun,
Atula Tejaswi,
Vasu Sharma,
Dipanwita Guhathakurta,
Sudheer Chava
EMNLP 2022 (Findings)
Paper /
Code
|
|
MONOPOLY: Financial Prediction from MONetary POLicY Conference Videos Using Multimodal Cues
Puneet Mathur,
Atula Tejaswi,
Malika Chhibber,
Ramit Sawhney,
Fu-Ming Guo,
Franck Dernoncourt,
Sanghamitra Dutta,
Dinesh Manocha
ACM Multimedia 2022
Paper /
Code
|
|
Towards Suicide Ideation Detection Through Online Conversational Context
Ramit Sawhney*,
Shivam Agarwal*,
Atula Tejaswi*,
Nikolaos Aletras,
Preslav Nakov,
Lucie Flek
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2022)
Paper /
Code
|
|
Orthogonal Multi-Manifold Enriching of Directed Networks
Ramit Sawhney*,
Shivam Agarwal*,
Atula Tejaswi*,
Kapil Pathak*
International Conference on Artificial Intelligence and Statistics (AISTATS 2022)
Paper /
Code
|
|
A Risk-Averse Mechanism for Suicidality Assessment on Social Media
Ramit Sawhney*,
Atula Tejaswi*,
Manas Gaur
Association for Computational Linguistics 2022 (ACL 2022)
Paper
|
|
The Impact of Differential Privacy on Group Disparity Mitigation
Victor Petrén Bach Hansen*,
Atula Tejaswi*
Ramit Sawhney,
Lucie Flek,
Anders Søgaard
PrivateNLP Workshop, NAACL 2022
Paper /
Code
|
|
Intermix: An Interference-Based Data Augmentation and Regularization Technique for Automatic Deep Sound Classification
Ramit Sawhney,
Atula Tejaswi
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2022)
Paper /
Code
|
Template from Jon Barron's website
|