michiyasunaga / BIFI
[ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair
☆111Updated last year
Related projects ⓘ
Alternatives and complementary repositories for BIFI
- Contrastive Code Representation Learning: functionality-based JavaScript embeddings through self-supervised learning☆167Updated 2 years ago
- Recent Advances in Programming Language Pre-Trained Models (PL-PTMs)☆57Updated 2 years ago
- Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].☆187Updated 2 years ago
- Official code of our work, AVATAR: A Parallel Corpus for Java-Python Program Translation.☆53Updated 3 months ago
- PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. W…☆87Updated 2 years ago
- This repo will contain replication package for the paper "Feeding Trees to Transformers for Code Completion"☆100Updated 2 years ago
- Implementation of the paper "Language-agnostic representation learning of source code from structure and context".☆167Updated 2 years ago
- The dataset for the variable-misuse task, used in the ICLR 2020 paper 'Global Relational Models of Source Code' [https://openreview.net/f…☆22Updated 4 years ago
- Code for "Learning Structural Edits via Incremental Tree Transformations" (ICLR'21)☆40Updated 3 years ago
- VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning☆38Updated last year
- ☆66Updated 2 years ago
- Releasing code for "ReCode: Robustness Evaluation of Code Generation Models"☆49Updated 8 months ago
- PyTorch's implementation of the code2seq model.☆61Updated 4 months ago
- ☆23Updated last year
- Code implementation for CoTexT: Multi-task Learning with Code-Text Transformer☆36Updated 3 years ago
- CoditT5: Pretraining for Source Code and Natural Language Editing☆28Updated last month
- Re-implementation of "CODE2SEQ: GENERATING SEQUENCES FROM STRUCTURED REPRESENTATIONS OF CODE"☆44Updated 4 months ago
- A collection of recent papers, benchmarks and datasets of AI4Code domain.☆54Updated 7 months ago
- Replication Code for "Self-Supervised Bug Detection and Repair" NeurIPS 2021☆108Updated 2 years ago
- Data and Code for Reproducing "Global Relational Models of Source Code"☆83Updated 3 years ago
- ☆43Updated 2 years ago
- A toolkit for pre-processing large source code corpora☆46Updated 2 years ago
- Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Sourc…☆61Updated 2 years ago
- Neural Code Translator provides instructions, datasets, and a deep learning infrastructure (based on seq2seq) that aims at learning code …☆39Updated 5 years ago
- [ICLR 2021] "Generating Adversarial Computer Programs using Optimized Obfuscations" by Shashank Srikant, Sijia Liu, Tamara Mitrovska, Shi…☆26Updated 3 years ago
- Models and datasets for annotated code search.☆33Updated last year
- Learning to Update Natural Language Comments Based on Code Changes: Artifact☆33Updated 4 years ago
- Contains the code and data for our #ICSE2022 paper titled as "CodeFill: Multi-token Code Completion by Jointly Learning from Structure an…☆14Updated 2 years ago
- JEMMA: An Extensible Java dataset for Many ML4Code Applications☆20Updated last year
- Code for generating the JuICe dataset.☆37Updated 3 years ago