Improving Neural Program Synthesis with Inferred Execution Traces

60 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Evaluating Large Language Models Trained on Code (2021, methodology): “More recent approaches like the Neural Program Interpreter (Reed & de Freitas, 2016; Shin et al., 2018; Pierrot et al., 2021) and Universal Transformer (Dehghani et al., 2019) found recurrence to be a useful component in program induction.”
IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis (2020, methodology): “In Bunel et al. (2018); Shin et al. (2018), two metrics have been used to evaluate the trained neural program synthesizer.”
Learning to Synthesize Programs as Interpretable and Generalizable Policies (2021, methodology): “To evaluate the proposed framework, we consider the Karel domain [23], as featured in [17, 19, 21], which features an agent navigating through a gridworld with walls and interacting with markers.”
SpreadsheetCoder: Formula Prediction from Semi-structured Context (2021, background): “…have been discussed, including input-output examples (Gulwani et al., 2012; Balog et al., 2017; Bunel et al., 2018; Bavishi et al., 2019; Shin et al., 2018; Chen et al., 2019), natural language descriptions (Gulwani & Marron, 2014; Yu et al., 2018; Yin et al., 2018; Lin et al., 2018;…”