Daniel Tarlow

Summary - TerpreT: A Probabilistic Programming Language for Program Induction

2016 · arXiv (Cornell University)

We study machine learning formulations of inductive program synthesis; that is, given input-output examples, synthesize source code that maps inputs to corresponding outputs. Our key contribution is TerpreT, a domain-specific language for expressing program synthesis …

Differentiable Programs with Neural Libraries

2016 · arXiv (Cornell University)

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore the benefits of inductive …

On-the-Fly Adaptation of Source Code Models using Meta-Learning

2020 · arXiv (Cornell University)

The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome. One of the most popular approaches for the adaptation of such models is dynamic evaluation. …

Repository-Level Prompt Generation for Large Language Models of Code

2022 · arXiv (Cornell University)

With the success of large language models (LLMs) of code and their use as code assistants (e.g. Codex used in GitHub Copilot), techniques for introducing domain-specific knowledge in the prompt design process become important. In …

Bimodal Modelling of Source Code and Natural Language

2015 · Edinburgh Research Explorer (University of Edinburgh)

We consider the problem of building probabilistic models that jointly model short natural language utterances and source code snippets. The aim is to bring together recent work on statistical modelling of source code and work …