Atula Tejaswi

I am a PhD student in Computer Science at The University of Texas at Austin, advised by Prof. Sujay Sanghavi. I received my Master's degree in CS from UT, and my Bachelor's degree in CSE from Manipal Institute of Technology. During this time, I have had the opportunity to work with Prof. Mrinmaya Sachan (ETH Zürich), Prof. Lucie Flek (University of Marburg), Prof. Marie-Jean Meurs (MITACS Globalink, University of Quebec in Montreal), and Prof. Aditya Gopalan (Indian Institute of Science), and Prof. Eunsol Choi (UT Austin/NYU).

CV   |   Google Scholar   |   Semantic Scholar   |   LinkedIn   |   Github   |   Colab Notebooks

Research Interests

My general interests are in Deep Learning and Natural Language Processing. My research aims to advance AI systems that exhibit genuine robustness, intelligence, and continuous adaptivity. I am interested in all critical aspects related to this, including innovative modeling techniques, strategic data utilization, rigorous benchmarking methodologies, and ensuring safety and inherent resilience.

I have previously worked on a broad range of NLP and ML application domains including Computational Social Science, Multimodal Learning, and Privacy-Preserving Deep Learning.

Papers

• RARe: Retrieval Augmented Retrieval With In-Context Examples
  Atula Tejaswi, Yoonsang Lee, Sujay Sanghavi*, Eunsol Choi*
  COLM 2025
  Code
• Exploring Design Choices for Building Language-Specific LLMs
  Atula Tejaswi*, Nilesh Gupta*, Eunsol Choi
  EMNLP 2024 (Findings)
  Code
• SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
  Vijay Lingam*, Atula Tejaswi*, Aditya Vavre*, Aneesh Shetty*, Gautham Krishna Gudur*, Joydeep Ghosh, Alex Dimakis, Eunsol Choi, Aleksandar Bojchevski, Sujay Sanghavi
  NeurIPS 2024
  Code
• Early Weight Averaging meets High Learning Rates for LLM Pre-training
  Sunny Sanyal*, Atula Tejaswi*, Jean Kaddour, Abhishek Kumar, Sujay Sanghavi
  COLM 2024
  Code
• The Impact of Differential Privacy on Group Disparity Mitigation
  Victor Petrén Bach Hansen*, Atula Tejaswi*, Ramit Sawhney, Lucie Flek, Anders Søgaard
  NAACL 2024 (Findings)
  Code
• RISE: Robust Early-exiting Internal Classifiers for Suicide Risk Evaluation
  Ritesh Soun, Atula Tejaswi, Ramit Sawhney, Nikolaos Aletras, Preslav Nakov
  LREC COLING 2024
  
• Saliency-Aware Interpolative Augmentation for Multimodal Financial Prediction
  Samyak Jain*, Parth Chhabra*, Atula Tejaswi*, Puneet Mathur, Ramit Sawhney, Shivam Agarwal, Preslav Nakov, Sudheer Chava, Dinesh Manocha
  LREC COLING 2024
  
• Learning Through Interpolative Augmentation of Dynamic Curvature Spaces
  Parth Chhabra*, Atula Tejaswi*, Shivam Agarwal, Ramit Sawhney, Megh Thakkar, Preslav Nakov, Sudheer Chava
  SIGIR 2023
  Code
• How Much User Context Do We Need? Privacy by Design in Mental Health NLP Applications
  Ramit Sawhney*, Atula Tejaswi*, Ivan Habernal, Lucie Flek
  ICWSM 2023
  
• 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)
  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
  Code
• Towards Suicide Ideation Detection Through Online Conversational Context
  Ramit Sawhney*, Shivam Agarwal*, Atula Tejaswi*, Nikolaos Aletras, Preslav Nakov, Lucie Flek
  SIGIR 2022
  Code
• Orthogonal Multi-Manifold Enriching of Directed Networks
  Ramit Sawhney*, Shivam Agarwal*, Atula Tejaswi*, Kapil Pathak*
  AISTATS 2022
  Code
• A Risk-Averse Mechanism for Suicidality Assessment on Social Media
  Ramit Sawhney*, Atula Tejaswi*, Manas Gaur
  ACL 2022
  
• Intermix: An Interference-Based Data Augmentation and Regularization Technique for Automatic Deep Sound Classification
  Ramit Sawhney, Atula Tejaswi
  ICASSP 2022
  Code