code generation

by Synced 2022-08-18 8

Microsoft, Penn U & UC San Diego’s TiCoder Framework Generates Code With 90.4% Consistency to User Intent

In the new paper Interactive Code Generation via Test-Driven User-Intent Formalization, a team from Microsoft Research, the University of Pennsylvania, and the University of California, San Diego proposes a workflow for test-driven user-intent formalization that leverages user feedback to generate code that is 90.40 percent consistent with user intent.

by Synced 2022-07-07 0

AI Machine Learning & Data Science Research

Salesforce’s CodeRL Achieves SOTA Code Generation Results With Strong Zero-Shot Transfer Capabilities

In the new paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning, a Salesforce Research team presents CodeRL, a novel framework for program synthesis tasks that employs pretrained language models (LMs) and deep reinforcement learning (RL) and achieves state-of-the-art performance on the challenging APPS benchmark while also demonstrating impressive zero-shot transfer capabilities.

by Synced 2022-02-04 2

AI Machine Learning & Data Science Research

DeepMind’s AlphaCode Generates Code at a Level Competitive With Human Programmers

A DeepMind research team presents AlphaCode, an automated code-generation system that can create novel solutions for programming problems that require deep reasoning and achieves a top 54.3% ranking in programming competitions.

by Synced 2021-07-13 2

AI Machine Learning & Data Science Nature Language Tech Research

OpenAI Fine-Tunes GPT-3 to Unlock Its Code Generation Potential for Difficult Problems

A research team from OpenAI proposes Codex, a specialized GPT model fine-tuned on publicly available code from GitHub that can produce functionally correct Python code bodies from natural language docstrings and could excel at a variety of coding tasks.