Publications (52)
A Survey on Query-based API Recommendation
Moshi Wei, Nima Shiri Harzevili, Alvine Boaye Belle +6
Application Programming Interfaces (APIs) are designed to help developers build software more effectively. Recommending the right APIs for specific tasks has gained increasing atte…
Decoding Human-LLM Collaboration in Coding: An Empirical Study of Multi-Turn Conversations in the Wild
Binquan Zhang, Li Zhang, Haoyuan Zhang +5
Large language models (LLMs) are increasingly acting as dynamic conversational interfaces, supporting multi-turn interactions that mimic human-like conversation and facilitate comp…
Revolutionizing Newcomers' Onboarding Process in OSS Communities: The Future AI Mentor
Xin Tan, Xiao Long, Yinghao Zhu +3
Onboarding newcomers is vital for the sustainability of open-source software (OSS) projects. To lower barriers and increase engagement, OSS projects have dedicated experts who prov…
RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation
Yang Liu, Li Zhang, Fang Liu +6
Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techn…
CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purification
Fangwen Mu, Junjie Wang, Zhuohao Yu +4
Neural code models have found widespread success in tasks pertaining to code intelligence, yet they are vulnerable to backdoor attacks, where an adversary can manipulate the victim…
ClarifyGPT: Empowering LLM-based Code Generation with Intention Clarification
Fangwen Mu, Lin Shi, Song Wang +5
We introduce a novel framework named ClarifyGPT, which aims to enhance code generation by empowering LLMs with the ability to identify ambiguous requirements and ask targeted clari…
Automated Generating Natural Language Requirements based on Domain Ontology
Ziyan Zhao, Li Zhang, Xiaoyun Gao +3
Software requirements specification is undoubtedly critical for the whole software life-cycle. Nowadays, writing software requirements specifications primarily depends on human wor…
Anharmonic corrections to the multiphonon deep-level charge capture ab initio calculations for semiconductors
Yao Xiao, Zi-Wu Wang, Lin Shi +3
Nonradiative carrier recombination at semiconductor deep centers is of great importance to both fundamental physics and device engineering. In this letter, we provide a revised ana…
Uncovering Weaknesses in Neural Code Generation
Xiaoli Lian, Shuaisong Wang, Jieping Ma +5
Code generation, the task of producing source code from prompts, has seen significant advancements with the advent of pre-trained large language models (PLMs). Despite these achiev…
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not…
EfficientEdit: Accelerating Code Editing via Edit-Oriented Speculative Decoding
Peiding Wang, Li Zhang, Fang Liu +7
Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity…
EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair
Fangwen Mu, Junjie Wang, Lin Shi +3
Automatically repairing software issues remains a fundamental challenge at the intersection of software engineering and AI. Although recent advances in Large Language Models (LLMs)…
Exponential mixing and Freidlin--Wentzell large deviation principle for Markov cocycles
Rongchang Liu, Kening Lu, Lin Shi +1
The paper establishes criteria for exponential mixing and a Freidlin‑Wentzell large deviation principle for Markov cocycles in random environments, and demonstrates these results f…
CURO: Curriculum Learning for Relative Overgeneralization
Lin Shi, Qiyuan Liu, Bei Peng
Relative overgeneralization (RO) is a pathology that can arise in cooperative multi-agent tasks when the optimal joint action's utility falls below that of a sub-optimal joint acti…
DistilCLIP-EEG: Enhancing Epileptic Seizure Detection Through Multi-modal Learning and Knowledge Distillation
Zexin Wang, Lin Shi, Haoyu Wu +3
Epilepsy is a prevalent neurological disorder marked by sudden, brief episodes of excessive neuronal activity caused by abnormal electrical discharges, which may lead to some menta…
Automatic Comment Generation via Multi-Pass Deliberation
Fangwen Mu, Xiao Chen, Lin Shi +2
Deliberation is a common and natural behavior in human daily life. For example, when writing papers or articles, we usually first write drafts, and then iteratively polish them unt…
Detection of Disease on Nasal Breath Sound by New Lightweight Architecture: Using COVID-19 as An Example
Jiayuan She, Lin Shi, Peiqi Li +9
Background. Infectious diseases, particularly COVID-19, continue to be a significant global health issue. Although many countries have reduced or stopped large-scale testing measur…
OpenThoughts-Agent: Data Recipes for Agentic Models
Negin Raoof, Richard Zhuang, Marianna Nezhurina +47
Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts…
ExAnte: A Benchmark for Ex-Ante Inference in Large Language Models
Yachuan Liu, Xiaochun Wei, Lin Shi +4
Large language models (LLMs) face significant challenges in ex-ante reasoning, where analysis, inference, or predictions must be made without access to information from future even…
CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation
Peiding Wang, Li Zhang, Fang Liu +4
Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existi…
On the Road to Personalized Code Intelligence: Portraiting and Assisting Developers Based on Their In-IDE Behaviors
Yuhong Liu, Yunhe Su, Zhipeng Peng +4
With the advent of large language models, research in automated software engineering has increasingly focused on leveraging these models to achieve a deeper semantic understanding…
A comparative study of ab initio nonradiative recombination rate calculations under different formalisms
Lin Shi, Ke Xu, Lin-Wang Wang
Nonradiative carrier recombination is of both great applied and fundamental importance.But the correct ab initio approaches to calculate it remains to be inconclusive. Here we used…
Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study
Bowen Li, Wenhan Wu, Ziwei Tang +13
Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isola…
Dialogue Disentanglement in Software Engineering: How Far are We?
Ziyou Jiang, Lin Shi, Celia Chen +2
Despite the valuable information contained in software chat messages, disentangling them into distinct conversations is an essential prerequisite for any in-depth analyses that uti…
The Good, the Bad, and the Missing: Neural Code Generation for Machine Learning Tasks
Jiho Shin, Moshi Wei, Junjie Wang +2
Machine learning (ML) has been increasingly used in a variety of domains, while solving ML programming tasks poses unique challenges because of the fundamentally different nature a…
An Empirical Study of Interaction Smells in Multi-Turn Human-LLM Collaborative Code Generation
Binquan Zhang, Li Zhang, Lin Shi +6
Large Language Models (LLMs) have revolutionized code generation, evolving from static tools into dynamic conversational interfaces that facilitate complex, multi-turn collaborativ…
Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation
Binquan Zhang, Li Zhang, Zhiwen Luo +4
Large language models (LLMs) have demonstrated impressive performance in code generation, particularly when augmented with chain-of-thought (CoT) prompting techniques. They break d…
PatUntrack: Automated Generating Patch Examples for Issue Reports without Tracked Insecure Code
Ziyou Jiang, Lin Shi, Guowei Yang +1
Security patches are essential for enhancing the stability and robustness of projects in the software community. While vulnerabilities are officially expected to be patched before…
Where is Your App Frustrating Users?
Yawen Wang, Junjie Wang, Hongyu Zhang +3
User reviews of mobile apps provide a communication channel for developers to perceive user satisfaction. Many app features that users have problems with are usually expressed by k…
Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge
Lin Shi, Chiyu Ma, Wenhua Liang +3
LLM-as-a-Judge has emerged as a promising alternative to human evaluators across various tasks, yet inherent biases - particularly position bias, the tendency to favor solutions ba…
Developer-Intent Driven Code Comment Generation
Fangwen Mu, Xiao Chen, Lin Shi +2
Existing automatic code comment generators mainly focus on producing a general description of functionality for a given code snippet without considering developer intentions. Howev…
VulRTex: A Reasoning-Guided Approach to Identify Vulnerabilities from Rich-Text Issue Report
Ziyou Jiang, Mingyang Li, Guowei Yang +2
Software vulnerabilities exist in open-source software (OSS), and the developers who discover these vulnerabilities may submit issue reports (IRs) to describe their details. Securi…
Vulnerability Identification by Harnessing Inter-connected Multi-Source Information
Liyou Chen, Hailong Sun, Xiang Gao +3
The utilization of third-party open-source libraries is widespread in modern software development. Due to the dependency relationships, vulnerabilities within open-source libraries…
SynAT: Enhancing Security Knowledge Bases via Automatic Synthesizing Attack Tree from Crowd Discussions
Ziyou Jiang, Lin Shi, Guowei Yang +3
Cyber attacks have become a serious threat to the security of software systems. Many organizations have built their security knowledge bases to safeguard against attacks and vulner…
FastCoder: Accelerating Repository-level Code Generation via Efficient Retrieval and Verification
Qianhui Zhao, Li Zhang, Fang Liu +6
Code generation is a latency-sensitive task that demands high timeliness. However, with the growing interest and inherent difficulty in repository-level code generation, most exist…
A First Look at Developers' Live Chat on Gitter
Lin Shi, Xiao Chen, Ye Yang +4
Modern communication platforms such as Gitter and Slack play an increasingly critical role in supporting software teamwork, especially in open source development.Conversations on s…
QC-SPHRAM: Quasi-conformal Spherical Harmonics Based Geometric Distortions on Hippocampal Surfaces for Early Detection of the Alzheimer's Disease
Anthony Hei-Long Chan, Yishan Luo, Lin Shi +1
We propose a disease classification model, called the QC-SPHARM, for the early detection of the Alzheimer's Disease (AD). The proposed QC-SPHARM can distinguish between normal cont…
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
Chiyu Ma, Enpei Zhang, Yilun Zhao +7
LLM-as-Judge has emerged as a scalable alternative to human evaluation, enabling large language models (LLMs) to provide reward signals in trainings. While recent work has explored…
Are We Building on the Rock? On the Importance of Data Preprocessing for Code Summarization
Lin Shi, Fangwen Mu, Xiao Chen +6
Code summarization, the task of generating useful comments given the code, has long been of interest. Most of the existing code summarization models are trained and validated on wi…
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…
Word differences in news media of lower and higher peace countries revealed by natural language processing and machine learning
Larry S. Liebovitch, William Powers, Lin Shi +3
Language is both a cause and a consequence of the social processes that lead to conflict or peace. Hate speech can mobilize violence and destruction. What are the characteristics o…
How Different AI Chatbots Behave? Benchmarking Large Language Models in Behavioral Economics Games
Yutong Xie, Yiyao Liu, Zhuang Ma +5
The deployment of large language models (LLMs) in diverse applications requires a thorough understanding of their decision-making strategies and behavioral patterns. As a supplemen…
Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
Xiangping Chen, Xing Hu, Yuan Huang +23
Researchers have recently achieved significant advances in deep learning techniques, which in turn has substantially advanced other research disciplines, such as natural language p…
Automatic Unit Test Generation for Deep Learning Frameworks based on API Knowledge
Arunkaleeshwaran Narayanan, Nima Shiri harzevili, Junjie Wang +3
Many automatic unit test generation tools that can generate unit test cases with high coverage over a program have been proposed. However, most of these tools are ineffective on de…
Addressing Overthinking in Large Vision-Language Models via Gated Perception-Reasoning Optimization
Xingjian Diao, Zheyuan Liu, Chunhui Zhang +6
Large Vision-Language Models (LVLMs) have exhibited strong reasoning capabilities through chain-of-thought mechanisms that generate step-by-step rationales. However, such slow-thin…
Invariant measures, periodic measures and pullback measure attractors of McKean-Vlasov stochastic reaction-diffusion equations on unbounded domains
Lin Shi, Jun Shen, Kening Lu +1
This paper deals with the long term dynamics of the non-autonomous McKean-Vlasov stochastic reaction-diffusion equations on R^n. We first prove the existence and uniqueness of pull…
VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
Shoubin Li, Xuyan Ma, Shuaiqun Pan +3
Documents often contain complex physical structures, which make the Document Layout Analysis (DLA) task challenging. As a pre-processing step for content extraction, DLA has the po…
BugListener: Identifying and Synthesizing Bug Reports from Collaborative Live Chats
Lin Shi, Fangwen Mu, Yumin Zhang +6
In community-based software development, developers frequently rely on live-chatting to discuss emergent bugs/errors they encounter in daily development tasks. However, it remains…
Pullback measure attractors and limiting behaviors of McKean-Vlasov stochastic delay lattice systems
Lin Shi, Jun Shen, Kening Lu
We study the long-term behavior of the distribution of the solution process to the non-autonomous McKean-Vlasov stochastic delay lattice system defined on the integer set $\mathbb{…
Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts
Chenyang Zhu, Bin Xiao, Lin Shi +2
The recent Segment Anything Model (SAM) represents a significant breakthrough in scaling segmentation models, delivering strong performance across various downstream applications i…
ISPY: Automatic Issue-Solution Pair Extraction from Community Live Chats
Lin Shi, Ziyou Jiang, Ye Yang +5
Collaborative live chats are gaining popularity as a development communication tool. In community live chatting, developers are likely to post issues they encountered (e.g., setup…
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
Yurong Wu, Fangwen Mu, Qiuhong Zhang +8
Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates th…