Learning to Execute

13 papers with code • 0 benchmarks • 0 datasets

This task has no description! Would you like to contribute one?

EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning

rajasekharmekala/query-rephrasing-subtask-cot 16 Sep 2023

On average, EchoPrompt improves the Zero-shot-CoT performance of code-davinci-002 by 5% in numerical tasks and 13% in reading comprehension tasks.

2
16 Sep 2023

Latent Space Representations of Neural Algorithmic Reasoners

mirjanic/nar-latent-spaces 17 Jul 2023

Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computation, usually by learning to execute algorithms.

4
17 Jul 2023

A Generalist Neural Algorithmic Learner

google-deepmind/clrs 22 Sep 2022

The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution.

355
22 Sep 2022

Unveiling Transformers with LEGO: a synthetic reasoning task

yizhangzzz/transformers-lego 9 Jun 2022

We study how the trained models eventually succeed at the task, and in particular, we manage to understand some of the attention heads as well as how the information flows in the network.

17
09 Jun 2022

The CLRS Algorithmic Reasoning Benchmark

deepmind/clrs 31 May 2022

Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms.

355
31 May 2022

Learning to Execute Actions or Ask Clarification Questions

zhengxiangshi/learntoask Findings (NAACL) 2022

In this paper, we extend the Minecraft Corpus Dataset by annotating all builder utterances into eight types, including clarification questions, and propose a new builder agent model capable of determining when to ask or execute instructions.

10
18 Apr 2022

Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions

google-research/runtime-error-prediction 7 Mar 2022

This presents an interesting machine learning challenge: can we predict runtime errors in a "static" setting, where program execution is not possible?

24
07 Mar 2022

Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics

ischubert/l2e NeurIPS 2021

Applications of Reinforcement Learning (RL) in robotics are often limited by high data demand.

3
15 Nov 2021

ProTo: Program-Guided Transformer for Program-Guided Tasks

sjtuytc/Neurips21-ProTo-Program-guided-Transformers-for-Program-guided-Tasks NeurIPS 2021

Furthermore, we propose the Program-guided Transformer (ProTo), which integrates both semantic and structural guidance of a program by leveraging cross-attention and masked self-attention to pass messages between the specification and routines in the program.

20
02 Oct 2021

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

google-research/google-research NeurIPS 2020

More practically, we evaluate these models on the task of learning to execute partial programs, as might arise if using the model as a heuristic function in program synthesis.

32,570
23 Oct 2020