ARiSE-Lab / CYCLE_OOPSLA_24Links
Open-source repository for the OOPSLA'24 paper "CYCLE: Learning to Self-Refine Code Generation"
☆10Updated last year
Alternatives and similar repositories for CYCLE_OOPSLA_24
Users that are interested in CYCLE_OOPSLA_24 are comparing it to the libraries listed below
Sorting:
- Reinforcement Learning for Repository-Level Code Completion☆39Updated last year
- ☆28Updated this week
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆62Updated last year
- Training and Benchmarking LLMs for Code Preference.☆35Updated 9 months ago
- [NeurIPS 2024] Evaluation harness for SWT-Bench, a benchmark for evaluating LLM repository-level test-generation☆54Updated last week
- StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback☆68Updated last year
- ☆35Updated 2 years ago
- ☆28Updated 7 months ago
- ☆28Updated 11 months ago
- ☆52Updated last year
- [EMNLP'22] Code for 'Exploring Representation-level Augmentation for Code Search'☆27Updated last year
- ☆67Updated 8 months ago
- e☆39Updated 4 months ago
- ☆38Updated 2 months ago
- Code for Benchmarking Language Model Agents for Data-Driven Science☆29Updated 10 months ago
- InstructCoder: Instruction Tuning Large Language Models for Code Editing | Oral ACL-2024 srw☆62Updated 10 months ago
- ☆17Updated last month
- Repoformer: Selective Retrieval for Repository-Level Code Completion (ICML 2024)☆58Updated 2 months ago
- NaturalCodeBench (Findings of ACL 2024)☆67Updated 10 months ago
- [EACL 2024] ICE-Score: Instructing Large Language Models to Evaluate Code☆79Updated last year
- ☆29Updated last year
- XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts☆35Updated last year
- Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding☆27Updated last year
- This is the official project of paper: Compress to Impress: Unleashing the Potential of Compressive Memory in Real-World Long-Term Conver…☆21Updated 9 months ago
- A distributed, extensible, secure solution for evaluating machine generated code with unit tests in multiple programming languages.☆56Updated 10 months ago
- [FORGE 2025] Graph-based method for end-to-end code completion with context awareness on repository☆65Updated last year
- Moatless Testbeds allows you to create isolated testbed environments in a Kubernetes cluster where you can apply code changes through git…☆15Updated 4 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆81Updated last year
- ☆15Updated last year
- This repository includes a benchmark and code for the paper "Evaluating LLMs at Detecting Errors in LLM Responses".☆30Updated last year