Sotabase

Career

· Research Intern, Meta2022–2022
· Research Intern, Microsoft Research2021–2021
· BA Programme Business Statistics, Sri Guru Nanak Dev Khalsa College2020–2023
· Research Intern, Borealis AI2019–2020
· Founder, KAP Digital2018–
· PhD in Computer Science, McGill University2018–
· Software Engineer, Alexa Algorithms, Amazon2016–2017
· Software Engineer, Alexa Machine Learning Platform, Amazon2015–2016
· Software Engineering Intern, Transactional Risk Management Services, Amazon2014–2014
· Master of Science, Computer Engineering, University of Florida2013–2015
· Software Engineer, Chatimity2011–2013
· System Software Engineer, Multimedia Audio Team, ST-Ericsson2010–2011
· B. Tech, Electronics and Communication Engineering, Motilal Nehru National Institute of Technology, Allahabad2006–2010

Publications (31)

BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
arXiv.org · 2022
276
cited
DataComp-LM: In search of the next generation of training sets for language models
Neural Information Processing Systems · 2024
238
cited
Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation
Findings · 2022
106
cited
OpenThoughts: Data Recipes for Reasoning Models
arXiv.org · 2025
96
cited
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
arXiv.org · 2025
62
cited
Director: Generator-Classifiers For Supervised Language Modeling
AACL · 2022
46
cited
Text Extraction from Document Images Using Edge Information
2009 Annual IEEE India Conference · 2009
46
cited
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback
Annual Meeting of the Association for Computational Linguistics · 2022
43
cited
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Neural Information Processing Systems · 2024
39
cited
Lexi: Self-Supervised Learning of the UI Language
Conference on Empirical Methods in Natural Language Processing · 2023
18
cited
X-MODDES (eXtended Multi Operator Delimiter Based Data Encryption Standard)
2010 Second International Conference on Future Networks · 2010
11
cited
Learning Lexical Subspaces in a Distributional Vector Space
Transactions of the Association for Computational Linguistics · 2020
10
cited
Contrastive Entropy: A new evaluation metric for unnormalized language models
2016
7
cited
The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation
arXiv.org · 2023
7
cited
A Compositional Approach to Language Modeling
arXiv.org · 2016
4
cited
Contrastive Perplexity: A new evaluation metric for sentence level language models
arXiv.org · 2016
3
cited
NormLens: Massively Multicultural MLLM Reasoning with Fine-Grained Social Awareness
1
cited
Allelopathic effect of Chenopodium murale towards Lens culinaris
2005
I MPROVING T EST -T IME S EARCH WITH B ACKTRACK - ING A GAINST I N -C ONTEXT V ALUE V ERIFIERS
Sotabase
Kushal Arora | Researcher Profile | Sotabase | Sotabase