Search Results for author: Jinjun Peng

Found 4 papers, 3 papers with code

CWEval: Outcome-driven Evaluation on Functionality and Security of LLM Code Generation

1 code implementation14 Jan 2025 Jinjun Peng, Leyi Cui, Kele Huang, Junfeng Yang, Baishakhi Ray

Large Language Models (LLMs) have significantly aided developers by generating or assisting in code writing, enhancing productivity across various tasks.

Code Generation

SemCoder: Training Code Language Models with Comprehensive Semantics Reasoning

1 code implementation3 Jun 2024 Yangruibo Ding, Jinjun Peng, Marcus J. Min, Gail Kaiser, Junfeng Yang, Baishakhi Ray

This approach led to the development of SemCoder, a Code LLM with only 6. 7B parameters, which shows competitive performance with GPT-3. 5-turbo on code generation and execution reasoning tasks.

Code Completion Code Generation +2

Quarl: A Learning-Based Quantum Circuit Optimizer

no code implementations17 Jul 2023 Zikun Li, Jinjun Peng, Yixuan Mei, Sina Lin, Yi Wu, Oded Padon, Zhihao Jia

Applying reinforcement learning (RL) to quantum circuit optimization raises two main challenges: the large and varying action space and the non-uniform state representation.

Reinforcement Learning (RL)

NeuRI: Diversifying DNN Generation via Inductive Rule Inference

1 code implementation4 Feb 2023 Jiawei Liu, Jinjun Peng, Yuyao Wang, Lingming Zhang

NeuRI finds 100 new bugs for PyTorch and TensorFlow in four months, with 81 already fixed or confirmed.

Decision Making Program Synthesis +1

Cannot find the paper you are looking for? You can Submit a new open access paper.