John Gouwar
YOU?
Author Swipe
View article: Scaling Optimization over Uncertainty via Compilation
Scaling Optimization over Uncertainty via Compilation Open
Probabilistic inference is fundamentally hard, yet many tasks require optimization on top of inference, which is even harder. We present a new optimization-via-compilation strategy to scalably solve a certain class of such problems. In par…
View article: Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs
Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs Open
Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software enginee…
View article: Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs
Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs Open
Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software enginee…
View article: MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation
MultiPL-E: A Scalable and Polyglot Approach to Benchmarking Neural Code Generation Open
Large language models have demonstrated the ability to generate both natural language and programming language text. Although contemporary code generation models are trained on corpora with several programming languages, they are tested us…
View article: MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation
MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation Open
Large language models have demonstrated the ability to generate both natural language and programming language text. Such models open up the possibility of multi-language code generation: could code generation models generalize knowledge f…