Scholar
Onkar Pandit
Google Scholar ID: tnk6ut0AAAAJ
INRIA Lille, France
Citations & Impact
Citations
290
H-index
6
i10-index
6
Publications
11
Co-authors
7
list available
Resume (English only)
Academic Achievements
- - Publication: Integrating Contextual and Commonsense Information for Automatic Discourse Understanding: Contributions to Temporal Relation Classification and Bridging Anaphora Resolution
- - Publication: Bilingual Adaptation of Monolingual Foundation Models
- - Publication: Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
- - Publication: Probing for Bridging Inference in Transformer Language Models
- - Publication: Integrating knowledge graph embeddings to improve mention representation for bridging anaphora resolution
- - Publication: Learning Rich Event Representations and Interactions for Temporal Relation Classification
Research Experience
- - Senior Applied Scientist, Apr. 2023 – Present, Inception Institute of AI, UAE
- - Project Scientist, Jul. 2016 – Nov. 2017, Indian Statistical Institute, Kolkata, India
- - Senior Member Technical Staff, Jul. 2012 – Jun. 2016, Oracle India Pvt. Ltd., Bangalore, India
Education
- - Ph.D. in Computer Science, University of Lille, France, Dec. 2017 - Sept. 2021, Advisors: Dr. Pascal Denis and Prof. Liva Ralaivola
- - M.Tech. in Electrical Engineering, Indian Institute of Technology (IIT), Kanpur, India, Jul. 2010 - Jun. 2012
- - B.Tech. in Electronics and Telecommunication Engineering, Shri Guru Gobind Singhji Institute of Engineering and Technology, Nanded, India, Jul. 2006 - Jun. 2010
Background
- Currently a Senior Applied Scientist at Inception Institute of AI, UAE, where he develops Large Language Models for Arabic and Hindi. He has open-sourced some of the first and best Arabic and Hindi LLMs—Jais and Nanda. He has also worked on enhancing math and reasoning abilities in LLMs and recently tackled challenges in weather and climate prediction. Currently, he is working on an exciting problem for the Oil & Gas industry, designing a domain-specific LLM and pushing the boundaries of Large Multi-modal Models.
