16 citations · 68 across the 60 of their papers we have counts for
73 papers
DolphinRouting: Cluster-Level Binary Routing for Disaggregated LLM Inference Serving
Yishuo Yuan, Shaoyu Yang, Chunrong Fang
Prefill-decode (PD) disaggregation isolates the two phases of large language model serving, but request-level path selection must account for prefill work, cache reuse, and decode…
Stateful Testing for Deep Learning Compilers
Jiatao Ge, Ruixiang Qian, Yibo Hu +5
Modern deep learning compilers compile models lazily and cache artifacts across invocations. Retained compiler state can make a later invocation incorrect even when it is correct i…
Grounding Deep Learning Framework Testing in Data Flow
Jiatao Ge, Yanzhou Mu, Yinglong Zou +3
Data flow underlies deep learning (DL) framework execution, including automatic differentiation and operator-fusion optimization. Bugs involving data flow can cause incorrect resul…
Beyond the Model: Demystifying Harness Effects in Software Engineering Agents
Haichuan Hu, Quanjun Zhang, Shengcheng Yu +5
Large Language Model (LLM)-based agents are increasingly used for software engineering tasks, yet their performance is not determined by the base model alone. The agent harness sub…
CacheReforge: Bounded Recovery for Stale KV Caches under Evolving Adapters
Yuhang Cao, Yanzhou Mu, Chunrong Fang +1
Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters evolve, cached states reflect…
Self-Evolving Coding Agents
Hao Zhou, Haichuan Hu, Tianyu Luo +5
Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and g…
Software Engineering for and with GUI Agent
Shengcheng Yu, Yuchen Ling, Junyang Xing +3
GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity of the field. GUI agents rema…
Breaking Customized LLMs for Coding: Automated Red Teaming for Instruction Backdoor Attacks
Yuchen Chen, Wei Cheng, Yuan Xiao +5
LLM customization platforms allow users to build task-specific models for code intelligence tasks by embedding instructions into system prompts, without modifying the underlying mo…
MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugs
Haichuan Hu, Chunrong Fang, Ye Shang +5
Automated Program Repair (APR) has benefited greatly from Large Language Models (LLMs), but existing LLM-based APR methods still struggle with multi-hunk bugs that require coordina…
Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation
Yuchen Chen, Wei Cheng, Yuan Xiao +7
LLM-based systems increasingly incorporate long-term memory to improve cross-session continuity. However, once insecure coding preferences are stored, they may silently influence s…
Understanding before Naming! Enhancing LLM-based Method Name Prediction with Code Summarization
Wei Liu, Weisong Sun, Tingting Xu +4
Method names are critical to software quality, affecting code comprehensibility, maintainability, and developer collaboration. However, manually designing meaningful method names i…
ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports
Quanjun Zhang, Yi Zheng, Ye Shang +5
Reproduction tests help developers confirm reported issues and provide executable feedback for issue resolution, yet issue reports in open-source projects rarely include such tests…
Multi-Agent LLM Collaboration for Unit Test Generation via Human-Testing-Inspired Workflows
Quanjun Zhang, Ye Shang, Siqi Gu +4
Recently, the emergence of Large Language Models (LLMs) has spurred a surge of research into automated unit test generation, yielding impressive performance and reducing manual eff…
Rise From The Ashes: LLM-based Static Analysis for Deep Learning Framework Bugs
Shaoyu Yang, Haifeng Lin, Chunrong Fang +6
Deep learning (DL) frameworks are critical AI infrastructures that often hide bugs with serious security implications. While dynamic approaches such as fuzzing are effective in unc…
Investigating Metamorphic Fuzz Oracle Enhancement via Large Language Models
Ruixiang Qian, Ding Yang, Zengxu Chen +4
Fuzz drivers are essential components of greybox fuzzing, as they encapsulate target interfaces, define test spaces, and largely determine fuzzing effectiveness. Existing fuzz driv…
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
Yuchen Chen, Weisong Sun, Haocheng Huang +11
Code Language Models (CodeLMs) have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical…
Execution-Grounded Security Testing for Coding Agents in Software Engineering Pipelines
Yifei Ge, Weisong Sun, Jinkun Xiao +8
Coding agents are increasingly integrated into system operations, where their tool use can directly modify project artifacts, execution environments, and the underlying system. For…
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
Yuchen Ling, Shengcheng Yu, Zhenyu Chen +1
Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environment…
SSDAU: Structured Semantic Data Augmentation for Joint Entity and Relation Extraction
Jiawei He, Mengyu Shi, Jiawei Liu +6
Joint Entity and Relation Extraction (JERE) is highly sensitive to training data quality, making data augmentation a natural way to improve generalization. However, existing augmen…
Probing Privacy Leaks in LLM-based Code Generation via Test Generation
Yifei Ge, Zhenpeng Chen, Weisong Sun +7
The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensiti…
Breaking, Stale, or Missing? Benchmarking Coding Agents on Project-Level Test Evolution
Ye Shang, Quanjun Zhang, Haichuan Hu +3
As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with pre-paired inputs, by…
Learning from Repair Experience: Self-Evolving Agents for Automated Vulnerability Repair
Haichuan Hu, Guoqing Xie, Quanjun Zhang +5
Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experie…
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
Yuan Xiao, Jiaming Wang, Yuchen Chen +8
The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage…
DuCodeMark: Dual-Purpose Code Dataset Watermarking via Style-Aware Watermark-Poison Design
Yuchen Chen, Yuan Xiao, Chunrong Fang +2
The proliferation of large language models for code (CodeLMs) and open-source contributions has heightened concerns over unauthorized use of source code datasets. While watermarkin…