On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “HearthStone”

A Retrieve-and-Edit Framework for Predicting Structured Outputsstat.ML

A framework that edits existing examples to generate structured outputs.

problem Generating complex outputs like code is hard.

method Retrieve a training example, edit it, and use a computationally efficient retrieval model.

result Retrieve-and-edit framework significantly boosts performance on code and card tasks.

structured outputs code generation retrieve-and-edit sequence-to-sequence retrieval model

2018-12-04abs ↗pdf ↗

A Grammar-Based Structural CNN Decoder for Code Generationcs.LG

A new CNN-based code generator outperforms RNNs by 5%.

problem Capturing long sequences in code generation using RNNs.

method Grammar-based structural CNN with tree-based and pre-order convolution modules.

result Significantly outperforms previous state-of-the-art methods by 5 percentage points.

code generation grammar-based convolutional neural network HearthStone semantic parsing

2018-11-14abs ↗pdf ↗

Abstract Syntax Networks for Code Generation and Semantic Parsingcs.CL

Tasks like code generation and semantic parsing require mapping unstructured (or partially structured) inputs to well-formed, executable outputs. We introduce abstract syntax networks, a modeling framework for these problems. The outputs are represented as abstract syntax trees (ASTs) and constructed by a decoder with …

2017-04-25abs ↗pdf ↗

Covariance Matrix Adaptation for the Rapid Illumination of Behavior Spacecs.LG

CMA-ME combines CMA-ES and MAP-Elites for better quality and diversity in continuous domains.

problem Finding a diverse set of high-quality solutions in complex continuous domains.

method Combines CMA-ES self-adaptation with MAP-Elites archiving and mapping.

result CMA-ME outperforms MAP-Elites in both quality and diversity of solutions.

Covariance Matrix Adaptation Quality Diversity Continuous Optimization Map-Elites Evolution Strategies

2019-12-05abs ↗pdf ↗