Scholar
H S V N S Kowndinya Renduchintala
Google Scholar ID: ekUSmaEAAAAJ
Research Associate, Media and Data Science Research, Adobe Inc.
Citations & Impact
Citations
42
H-index
3
i10-index
1
Publications
4
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- October 2023, Presented INGENIOUS at EMNLP 2023; May 2024, SMART: Submodular Data Mixtures for Instruction Tuning accepted to ACL 2024 (Findings); August 2024, Presented SMART in person at ACL 2024; November 2024, POSIX: A Prompt Sensitivity Index for Large Language Models accepted to EMNLP 2024 (Findings); July 2025, On the Effect of Instruction Tuning Loss on Generalization published in TACL.
Research Experience
- July 2023 - Present, Research Associate at Media and Data Science Research (MDSR) Lab, Adobe Inc.; May 2022 - July 2023, Research Intern at Media and Data Science Research (MDSR) Lab, Adobe Inc.
Education
- July 2019 - August 2023, Indian Institute of Technology Bombay, Bachelor's degree (with Honors) in Computer Science and Engineering, Advisors: Prof. Ganesh Ramakrishnan and Prof. Rishabh Iyer, Undergraduate Thesis: Data-Efficient Pretraining of Language models using Submodular Functions.
Background
- Research interests include data efficiency and human-cognition inspired architectures/algorithms in NLP; also interested in interpretability of LMs and adaptation of LMs post-pretraining (e.g., instruction tuning). Long-term research goal is to develop provably beneficial intelligent computational agents that can excel at both formal linguistic competence and functional linguistic competence.
Miscellany
- Best way to contact is via e-mail.
