Recent advances in Large Language Models (LLM) have made automatic code generation possible for real-world programming tasks in general-purpose programming languages …
D Jayagopal, J Lubin, SE Chasins - … of the 35th Annual ACM Symposium …, 2022 - dl.acm.org
Modern program synthesizers are increasingly delivering on their promise of lightening the burden of programming by automatically generating code, but little research has addressed …
Exploratory data science largely happens in computational notebooks with dataframe APIs, such as pandas, that support flexible means to transform, clean, and analyze data. Yet …
Programming-by-example (PBE) has become an increasingly popular component in software development tools, human-robot interaction, and end-user programming. A long …
Modern visualization tools aim to allow data analysts to easily create exploratory visualizations. When the input data layout conforms to the visualization design, users can …
With most modern visualization tools, authors need to transform their data into tidy formats to create visualizations they want. Because this requires experience with programming or …
We consider the quantitative problem of obtaining lower-bounds on the probability of termination of a given non-deterministic probabilistic program. Specifically, given a non …
In this paper, we present a new program synthesis algorithm based on reinforcement learning. Given an initial policy (ie statistical model) trained off-line, our method uses this …
J Lubin, N Collins, C Omar, R Chugh - Proceedings of the ACM on …, 2020 - dl.acm.org
We present a system called Smyth for program sketching in a typed functional language whereby the concrete evaluation of ordinary assertions gives rise to input-output examples …