Reshinth Adithyan

I’m a research engineer at Stability AI based out of London. I’m part of the Code.AI Team at Stability AI, I predominantly work on large-scale pretraining of code models. During my time at Stability AI, I’ve been working on Stable Code suite of models. I was also one of the core members of Code.AI, a community of researchers and engineers working on Code Intelligence and Machine Learning aided Code Completion systems. I was a major contributor to one of the first open source Code Language Model Code Clippy.

Email  /  Scholar  /  Twitter  /  Github

Research

I’m interested in,

• Large-scale pretraining of language models
• CodeLMs and Qualitative Evaluations
• Interpreter grounded CodeLMs

Previously

I was part of,

• 2022-2023 - Research Engineer @ Saama Technologies, India - Focusing on ML aided Program Synthesis to solve clinical transformations.
• 2019-2022 - Research Engineer @ Mastercraft Labs, TCS, India - Focusing on ML aided Static Analysis for COBOL.
• 2019 - Research Intern @ Mastercraft Labs, TCS, India - Focusing on ML aided Static Analysis for COBOL.

Publications

• Stable Code Technical Report
• Stable LM 2 1.6B Technical Report
• Method and system for translation of codes based on semantic similarity
• Method and system for inferencing logic out of an application source
• Method and system for extracting natural language elements embedded in application source code