Neural Program Lattices

By Chengtao Li, Daniel Tarlow, Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman. 2016

34 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.

Citations in the corpus

Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions (2018, background): “…2016; Chang et al., 2016), playing games (Denil et al., 2017; Kansky et al., 2017), learning algorithms (Bošnjak et al., 2017; Cai et al., 2017; Li et al., 2016; Reed & De Freitas, 2015), visual understanding (Ellis et al., 2017; Johnson et al., 2017), and natural language processing (Andreas…”
VirtualHome: Simulating Household Activities Via Programs (2018, background): “There is increased interest in generating and interpreting source code [11].”
Neural Program Meta-Induction (2017, methodology): “tures Applied to Program Induction NTM [7], Stack RNN [11], NRAM [12] Neural Transducers [8], Learn Algo [21] 3337 Others [4, 20, 2, 13] Trace-Augmented Induction NPI [18] 3733 Recursive NPI [3], NPL [14] 3737 Non Example-Driven Induction (e.g., Natural Language-Driven Induction) Inducing Latent Pro”
Towards Synthesizing Complex Programs From Input-Output Examples (2017, background): “…Zaremba et al., 2016; Zaremba & Sutskever, 2015), but in these works, either extra supervision on execution traces is needed during training (Reed & De Freitas, 2016; Cai et al., 2017; Li et al., 2017), or the trained model cannot generalize well (Zaremba et al., 2016; Zaremba & Sutskever, 2015).”
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (2023, unknown): “Historically, outcome-based approaches focused on algorithmic tasks (Li et al., 2016; Cai et al., 2017; Yu et al., 2023a), while recent research demonstrates the efficacy of reward models or validators in enhancing model performance (Cobbe et al., 2021; Wang et al., 2023a;b; Li et al., 2022).”
Recent Advances in Neural Program Synthesis (2018, background): “The important result is that NPL is able to achieve similar performance to the NPI with this reduced supervision strength, and this represents another incremental step towards practical neural program induction.”
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis (2018, background): “Some exceptions to this include Neural Programmer Interpreters (Reed and de Freitas, 2016) and its extensions (Li et al., 2017; Cai et al., 2017) that learn from program traces rather than only examples.”
Solving math word problems with process- and outcome-based feedback (2022, unknown): “In contrast, Neural Programmer-Interpreters (Reed and De Freitas, 2015; Li et al., 2016; Cai et al., 2017) are trained to imitate each step in an execution trace, which can then be chained together.”
Execution-Guided Neural Program Synthesis (2018, background): “Synthesizing a program from input-output examples is an important challenging problem with many applications (Devlin et al., 2017b; Gulwani et al., 2012; Gulwani, 2011; Bunel et al., 2018; Chen et al., 2018; Cai et al., 2017; Li et al., 2017; Reed & De Freitas, 2016; Zaremba et al., 2016; Zaremba & ”