Search Results for author: Chao Peng

Found 26 papers, 12 papers with code

Open-Book Neural Algorithmic Reasoning

1 code implementation30 Dec 2024 Hefei Li, Chao Peng, Chenyang Xu, Zhengfeng Yang

Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks.

CodeRepoQA: A Large-scale Benchmark for Software Engineering Question Answering

1 code implementation19 Dec 2024 Ruida Hu, Chao Peng, Jingyi Ren, Bo Jiang, Xiangxin Meng, Qinyun Wu, Pengfei Gao, Xinchen Wang, Cuiyun Gao

In this work, we introduce CodeRepoQA, a large-scale benchmark specifically designed for evaluating repository-level question-answering capabilities in the field of software engineering.

Question Answering

A Context-Enhanced Framework for Sequential Graph Reasoning

1 code implementation12 Dec 2024 Shuo Shi, Chao Peng, Chenyang Xu, Zhengfeng Yang

The paper studies sequential reasoning over graph-structured data, which stands as a fundamental task in various trending fields like automated math problem solving and neural graph algorithm learning, attracting a lot of research interest.

Math

DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production

no code implementations11 Dec 2024 Xiaoyun Liang, Jingyi Ren, Jiayi Qi, Chao Peng, Bo Jiang

Large Language Models (LLMs) have become increasingly integral to enhancing developer productivity, particularly in code generation, comprehension, and repair tasks.

Code Generation Question Answering

Go-Oracle: Automated Test Oracle for Go Concurrency Bugs

no code implementations11 Dec 2024 Foivos Tsimpourlas, Chao Peng, Carlos Rosuero, Ping Yang, Ajitha Rajan

Our approach involves collecting both passing and failing execution traces from various subject Go programs.

ContextModule: Improving Code Completion via Repository-level Contextual Information

no code implementations11 Dec 2024 Zhanming Guan, Junlin Liu, Jierui Liu, Chao Peng, Dexin Liu, Ningyuan Sun, Bo Jiang, Wenchao Li, Jie Liu, Hang Zhu

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time.

Code Completion

An Empirical Study on LLM-based Agents for Automated Bug Fixing

no code implementations15 Nov 2024 Xiangxin Meng, Zexiong Ma, Pengfei Gao, Chao Peng

Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in addressing software defects by engaging in development environment interaction, iterative validation and code modification.

Bug fixing Fault localization

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning

no code implementations18 Oct 2024 Lang Cao, Chao Peng, Yitong Li

However, the introduction of step-by-step Chain-of-Thought (CoT) inference has significantly advanced the mathematical capabilities of LLMs.

Math Mathematical Reasoning

MarsCode Agent: AI-native Automated Bug Fixing

no code implementations2 Sep 2024 Yizhou Liu, Pengfei Gao, Xinchen Wang, Jie Liu, Yexuan Shi, Zhao Zhang, Chao Peng

Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, including code completion, test generation, and bug fixing.

Bug fixing Code Completion +2

RepoMasterEval: Evaluating Code Completion via Real-World Repositories

no code implementations7 Aug 2024 Qinyun Wu, Chao Peng, Pengfei Gao, Ruida Hu, Haoyu Gan, Bo Jiang, Jinhe Tang, Zhiwen Deng, Zhanming Guan, Cuiyun Gao, Xia Liu, Ping Yang

Our empirical evaluation on 6 state-of-the-art models shows that test argumentation is critical in improving the accuracy of the benchmark and RepoMasterEval is able to report difference in model performance in real-world scenarios.

Code Completion Code Generation +1

Multi-Objective Sizing Optimization Method of Microgrid Considering Cost and Carbon Emissions

no code implementations11 Jun 2024 Xiang Zhu, Guangchun Ruan, Hua Geng, Honghai Liu, Mingfei Bai, Chao Peng

Microgrid serves as a promising solution to integrate and manage distributed renewable energy resources.

Diversity

Hawkeye: Change-targeted Testing for Android Apps based on Deep Reinforcement Learning

no code implementations4 Sep 2023 Chao Peng, Zhengwei Lv, Jiarong Fu, Jiayuan Liang, Zhao Zhang, Ajitha Rajan, Ping Yang

We find that Hawkeye is able to generate GUI event sequences targeting changed functions more reliably than FastBot2 and ARES for the open source Apps and the large commercial App.

Deep Reinforcement Learning reinforcement-learning

CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility

1 code implementation19 Jul 2023 Guohai Xu, Jiayi Liu, Ming Yan, Haotian Xu, Jinghui Si, Zhuoran Zhou, Peng Yi, Xing Gao, Jitao Sang, Rong Zhang, Ji Zhang, Chao Peng, Fei Huang, Jingren Zhou

In this paper, we present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs in terms of both safety and responsibility criteria.

An End-to-End Network for Panoptic Segmentation

no code implementations CVPR 2019 Huanyu Liu, Chao Peng, Changqian Yu, Jingbo Wang, Xu Liu, Gang Yu, Wei Jiang

Panoptic segmentation, which needs to assign a category label to each pixel and segment each object instance simultaneously, is a challenging topic.

Panoptic Segmentation Segmentation

DetNet: Design Backbone for Object Detection

no code implementations ECCV 2018 Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

(1) Recent object detectors like FPN and RetinaNet usually involve extra stages against the task of image classification to handle the objects with various scales.

Classification General Classification +7

Learning a Discriminative Feature Network for Semantic Segmentation

3 code implementations CVPR 2018 Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction.

Semantic Segmentation Thermal Image Segmentation

DetNet: A Backbone network for Object Detection

2 code implementations17 Apr 2018 Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection.

Classification General Classification +7

ExFuse: Enhancing Feature Fusion for Semantic Segmentation

no code implementations ECCV 2018 Zhenli Zhang, Xiangyu Zhang, Chao Peng, Dazhi Cheng, Jian Sun

Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance.

Ranked #4 on Semantic Segmentation on PASCAL VOC 2012 val (using extra training data)

Segmentation Semantic Segmentation

MegDet: A Large Mini-Batch Object Detector

6 code implementations CVPR 2018 Chao Peng, Tete Xiao, Zeming Li, Yuning Jiang, Xiangyu Zhang, Kai Jia, Gang Yu, Jian Sun

The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design.

Object object-detection +1

Light-Head R-CNN: In Defense of Two-Stage Object Detector

5 code implementations20 Nov 2017 Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun

More importantly, simply replacing the backbone with a tiny network (e. g, Xception), our Light-Head R-CNN gets 30. 7 mmAP at 102 FPS on COCO, significantly outperforming the single-stage, fast detectors like YOLO and SSD on both speed and accuracy.

Vocal Bursts Valence Prediction

Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network

2 code implementations CVPR 2017 Chao Peng, Xiangyu Zhang, Gang Yu, Guiming Luo, Jian Sun

One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e. g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity.

Semantic Segmentation

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