Papers with Code 아카이브

Code Completion

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

1

평가표

6

보존된 평가 기록

28

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/facebookresearch/CodeGen

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/ibm/data-prep-kit

Scaling Granite Code Models to 128K Context

https://github.com/kilimanj4r0/code-summarization-beyond-function-level

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/leiluk1/codesearcher

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

https://github.com/lianjiatech/belle

Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences

https://github.com/mwcvitkovic/open-vocabulary-learning-on-source-code-with-a-graph-structured-cache--code-preprocessor

Open Vocabulary Learning on Source Code with a Graph-Structured Cache

https://github.com/nadiinchi/dynamic_embeddings

On the Embeddings of Variables in Recurrent Neural Networks for Source Code

https://github.com/naver/disco

Energy-Based Models for Code Generation under Compilability Constraints

https://github.com/ojiyumm/longbench_rwkv

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

https://github.com/oleges1/code-completion

Code Completion with Neural Attention and Pointer Networks

https://github.com/pwc-1/Paper-10/tree/main/starcoder2

StarCoder 2 and The Stack v2: The Next Generation

https://github.com/ruc-nlpir/flashrag

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

https://github.com/sberbank-ai/fusion_brain_aij2021

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/scientific-computing-lab-nrcn/mpi-rigen

MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers

https://github.com/snorkel-ai/long-context-eval

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

https://github.com/soran-ghaderi/torchebm

Energy-Based Models for Code Generation under Compilability Constraints

https://github.com/superli3/CYRMPR

Neural Software Analysis

https://github.com/superli3/codenavi

Neural Software Analysis

https://github.com/talkad/OMPify

Scope is all you need: Transforming LLMs for HPC Code

https://github.com/tihonovcore/model

Structural Language Models of Code

https://github.com/v587su/CodeMark

CodeMark: Imperceptible Watermarking for Code Datasets against Neural Code Completion Models

https://github.com/yueyuel/programgen-lms-reliability

CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation

https://github.com/zysszy/TreeGen

A Syntax-Guided Edit Decoder for Neural Program Repair

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.