guanziju/codellm

Name	Time	HumanEval	MBPP	Paper	link
CodeX	2107			Evaluating Large Language Models Trained on Code
CodeT5	2109			CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
JuPyT5	2201			Training and Evaluating a Jupyter Notebook Data Science Assistant
PolyCoder	2202			A Systematic Evaluation of Large Language Models of Code
AlphaCode	2203			Competition-Level Code Generation with AlphaCode
CodeGen	2203			CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
InCoder	2204			InCoder: A Generative Model for Code Infilling and Synthesis
MBR	2204			Natural Language to Code Translation with Execution
PyCodeGPT	2206			CERT:Continual Pre-Training on Sketches for Library-Oriented Code Generation
CodeRL	2207			CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning
PanguCoder	2207			PanGu-Coder: Program Synthesis with Function-Level Language Modeling
Coder Reviewer Reranking	2211			Coder Reviewer Reranking for Code Generation
GPT-3.5	2211
ERNIECode	2212			ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages
PPOCoder	2301			Execution-based Code Generation using Deep Reinforcement Learning
SantaCoder	2301			SantaCoder: don't reach for the stars!
Lever	2302			LEVER: Learning to Verify Language-to-Code Generation with Execution
svGen	2302			Large Language Models for Code: Security Hardening and Adversarial Testing
CodeGeeX	2303			CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Evaluations on HumanEval-X
GPT-4	2303			GPT-4 Technical Report
Reflexion(GPT4)	2303			Reflexion: Language Agents with Verbal Reinforcement Learning
Self-Debug	2304			Teaching Large Language Models to Self-Debug
ANPL	2305			ANPL: Towards Natural Programming with Interactive Decomposition
ChainCoder	2305			Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
CodeGen2	2305			CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
CodeT5+	2305			CodeT5+: Open Code Large Language Models for Code Understanding and Generation
StarCoder	2305			StarCoder: may the source be with you!
Phi1	2306			Textbooks Are All You Need
WizardCoder	2306			WizardCoder: Empowering Code Large Language Models with Evol-Instruct
PanguCoder2	2307			PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
CodeLlama	2308			Code Llama: Open Foundation Models for Code
OctoPack	2308			OctoPack: Instruction Tuning Code Large Language Models
Phi1.5	2309			Textbooks Are All You Need II: phi-1.5 technical report
CodeChain	2310			CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
CodeFuse	2310			CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
L2MAC	2310			L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
Intervenor	2311			INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair
MFTCoder	2311			MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning
RLTF	2311			RLTF: Reinforcement Learning from Unit Test Feedback
SRank	2311			Neural Code Generation Enhancement via Functional Overlap Reranking
AgentCoder	2312			AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
AlphaCode2	2312			AlphaCode 2 Technical Report
MagicCoder	2312			Magicoder: Source Code Is All You Need
MoTCoder	2312			MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
WaveCoder	2312			WaveCoder: Widespread And Versatile Enhanced Instruction Tuning with Refined Data Generation
AlphaCodium	2401			Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering
AST-T5	2401			AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
DeepSeekCoder	2401			DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
JumpCoder	2401			JumpCoder: Go Beyond Autoregressive Coder via Online Modification
Personalised Distillation	2401			Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generation
ToolGen	2401			Teaching Code LLMs to Use Autocompletion Tools in Repository-Level Code Generation
CodeS	2402			CodeS: Towards Building Open-source Language Models for Text-to-SQL
LDB	2402			LDB: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
OpenCodeInterpreter	2402			OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
StarCoder2	2402			StarCoder 2 and The Stack v2: The Next Generation
StepCoder	2402			StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
CodeShell	2403			CodeShell Technical Report
LCG	2403			When LLM-based Code Generation Meets the Software Development Process
ProCoder	2403			Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
QwenCoder1.5	2404
Self-Organized Agents	2404			Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization
StableCode	2404			Stable Code Technical Report