Publications (36)
Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs
Yujia Chen, Yang Ye, Zhongqi Li +2
Large code models (LCMs) have remarkably advanced the field of code generation. Despite their impressive capabilities, they still face practical deployment issues, such as high inf…
SSIF: Learning Continuous Image Representation for Spatial-Spectral Super-Resolution
Gengchen Mai, Ni Lao, Weiwei Sun +7
Existing digital sensors capture images at fixed spatial and spectral resolutions (e.g., RGB, multispectral, and hyperspectral images), and each combination requires bespoke machin…
Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark
Dewu Zheng, Yanlin Wang, Ensheng Shi +4
With the rapid advancement of large language models (LLMs), extensive research has been conducted to investigate the code generation capabilities of LLMs. However, existing efforts…
RLCoder: Reinforcement Learning for Repository-Level Code Completion
Yanlin Wang, Yanli Wang, Daya Guo +4
Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrieval-augme…
Predicting Neighbor Distribution in Heterogeneous Information Networks
Yuchi Ma, Ning Yang, Chuan Li +2
Recently, considerable attention has been devoted to the prediction problems arising from heterogeneous information networks. In this paper, we present a new prediction task, Neigh…
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
Tianyue Jiang, Yanlin Wang, Xin He +7
While Large Language Models have greatly advanced automated issue resolution, existing agent-based methods exhibit a fundamental limitation in their insufficient exploration of rep…
Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
Yanchen Wu, Tenghui Lin, Yingli Zhou +7
Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), whe…
CodeR: Issue Resolving with Multi-Agent and Task Graphs
Dong Chen, Shaoxin Lin, Muhan Zeng +14
GitHub issue resolving recently has attracted significant attention from academia and industry. SWE-bench is proposed to measure the performance in resolving issues. In this paper,…
RepoTransBench: A Real-World Multilingual Benchmark for Repository-Level Code Translation
Yanli Wang, Yanlin Wang, Suiquan Wang +8
Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source reposito…
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
Jiawei Yu, Yixiang Fang, Xilin Liu +1
Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their per…
When to Stop? Towards Efficient Code Generation in LLMs with Excess Token Prevention
Lianghong Guo, Yanlin Wang, Ensheng Shi +6
Code generation aims to automatically generate code snippets that meet given natural language requirements and plays an important role in software development. Although Code LLMs h…
Corn Yield Prediction based on Remotely Sensed Variables Using Variational Autoencoder and Multiple Instance Regression
Zeyu Cao, Yuchi Ma, Zhou Zhang
In the U.S., corn is the most produced crop and has been an essential part of the American diet. To meet the demand for supply chain management and regional food security, accurate…
Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs
CodeArts Model Team, Yang Ye, Jingyuan Tan +24
Training effective software engineering agents requires large volumes of task-specific trajectories, incurring substantial data construction costs. Inspired by the "Less-Is-More" h…
OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution
Lianghong Guo, Wei Tao, Runhan Jiang +7
The GitHub issue resolution task aims to resolve issues reported in repositories automatically. With advances in large language models (LLMs), this task has gained increasing atten…
Towards Mitigating API Hallucination in Code Generated by LLMs with Hierarchical Dependency Aware
Yujia Chen, Mingyu Chen, Cuiyun Gao +3
Application Programming Interfaces (APIs) are crucial in modern software development. Large Language Models (LLMs) assist in automated code generation but often struggle with API h…
CoderEval: A Benchmark of Pragmatic Code Generation with Generative Pre-trained Models
Hao Yu, Bo Shen, Dezhi Ran +7
Code generation models based on the pre-training and fine-tuning paradigm have been increasingly attempted by both academia and industry, resulting in well-known industrial models…
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta +19
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i.e. the synthesis of programming language solut…
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models
Jiajun Wu, Jian Yang, Wei Zhang +6
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive l…
SimpleDevQA: Benchmarking Large Language Models on Development Knowledge QA
Jing Zhang, Lianghong Guo, Yanlin Wang +7
The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide natural language answers to knowledge-seeking questions during software development. To investi…
In-depth Analysis of Graph-based RAG in a Unified Framework
Yingli Zhou, Yaodong Su, Youran Sun +8
Graph-based Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs), improving their factual accuracy, adaptab…
Harvesting AlphaEarth: Benchmarking the Geospatial Foundation Model for Agricultural Downstream Tasks
Yuchi Ma, Yawen Shen, Anu Swatantran +1
Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introdu…
DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning
Yanlin Wang, Jiadong Wu, Tianyue Jiang +7
Large language models (LLMs) have demonstrated impressive capabilities in code generation by leveraging retrieval-augmented generation (RAG) methods. However, the computational cos…
FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments
Fang Liu, Zhenwei Liu, Qianhui Zhao +6
Providing personalized and timely feedback for student's programming assignments is useful for programming education. Automated program repair (APR) techniques have been used to fi…
Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models
Yanlin Wang, Tianyue Jiang, Mingwei Liu +5
Large language models (LLMs) have brought a paradigm shift to the field of code generation, offering the potential to enhance the software development process. However, previous re…
Learning county from pixels: corn yield prediction with attention-weighted multiple instance learning
Xiaoyu Wang, Yuchi Ma, Qunying Huang +2
Remote sensing technology has become a promising tool in yield prediction. Most prior work employs satellite imagery for county-level corn yield prediction by spatially aggregating…
ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation
Sicong Liu, Yanxian Huang, Mingwei Liu +6
Code generation tasks aim to automate the conversion of user requirements into executable code, significantly reducing manual development efforts and enhancing software productivit…
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Fang Liu, Yang Liu, Lin Shi +5
The rise of Large Language Models (LLMs) has significantly advanced various applications on software engineering tasks, particularly in code generation. Despite the promising perfo…
Agents in Software Engineering: Survey, Landscape, and Vision
Yanlin Wang, Wanjun Zhong, Yanxian Huang +7
In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engine…
Hue: A User-Adaptive Parser for Hybrid Logs
Junjielong Xu, Qiuai Fu, Zhouruixing Zhu +4
Log parsing, which extracts log templates from semi-structured logs and produces structured logs, is the first and the most critical step in automated log analysis. While existing…
ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
Shu Wang, Yixiang Fang, Yingli Zhou +2
Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving question-answer (QA) tasks. The state-of-t…
Towards an Understanding of Context Utilization in Code Intelligence
Yanlin Wang, Kefeng Duan, Dewu Zheng +9
Code intelligence is an emerging domain in software engineering, aiming to improve the effectiveness and efficiency of various code-related tasks. Recent research suggests that inc…
EffiReasonTrans: RL-Optimized Reasoning for Code Translation
Yanlin Wang, Rongyi Ou, Yanli Wang +6
Code translation is a crucial task in software development and maintenance. While recent advancements in large language models (LLMs) have improved automated code translation accur…
HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation
Dewu Zheng, Yanlin Wang, Ensheng Shi +4
To evaluate the repository-level code generation capabilities of Large Language Models (LLMs) in complex real-world software development scenarios, many evaluation methods have bee…
What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond
Wenchao Gu, Juntao Chen, Yanlin Wang +6
Repository-level code generation remains challenging due to complex code dependencies and the limitations of large language models (LLMs) in processing long contexts. While retriev…
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
Yujia Chen, Yang Ye, Xiao Chu +2
Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale…
AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion
Tianyue Jiang, Yanli Wang, Yanlin Wang +5
Repository-level code completion remains a challenging task for existing code large language models (code LLMs) due to their limited understanding of repository-specific context an…