3 citations · 7 across the 20 of their papers we have counts for
23 papers
Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents
Junkai Lin, Ge Xu, Zheng Xu +2
Large language model (LLM) agents have shown strong capabilities in interactive problem solving, tool use, and long-horizon task execution. However, they may also acquire sensitive…
Generalizable Model Editing Could Be More Than Direct Generalization
Xiaotian Ye, Chunyao Yang, Xiaohan Wang +4
A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior…
Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail
Gou Tan, Pengfei Chen, Zhensu Sun +9
Runtime error healing lets a crashed program continue by generating code that repairs its live runtime state. Recent work shows that LLMs can generate such healing code, but it is…
AgentExecutor: Partial Code Execution via Agentic Context Generation
Junkai Chen, Chengran Yang, Xing Hu +3
Executing code snippets is essential for dynamic program analysis, but it remains challenging to execute an arbitrary code snippet due to issues like missing context and incomplete…
Exploring and Bridging Knowledge Holes in Unlearned Multimodal Large Language Models
Junxiang You, Junkai Chen, Yuhao He +3
Machine unlearning offers a promising approach to remove unsafe content from Multimodal Large Language Models (MLLMs), yet ensuring the precision of unlearning remains a persistent…
Toward Fine-Grained Forgetting:Attribute Unlearning for Multimodal Large Language Models
Junkai Lin, Junkai Chen, Siqi Hou +6
Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowledge while preserving model utilit…
SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements
Pengyu Xue, He Yang Yuan, Xin Wang +6
Although coding agents have achieved impressive performance on correctness-oriented benchmarks, their ability to make behavior-preserving non-functional improvements (NFIs) remains…
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
Junkai Chen, Yuhao He, Junxiang You +3
Multimodal Large Language Models (MLLMs) have achieved remarkable progress on vision-language tasks, but they may also memorize and expose sensitive or restricted knowledge, raisin…
Visual-Advantage On-Policy Distillation for Vision-Language Models
Ruiqi Liu, Xiaolei Lv, Gengsheng Li +8
On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-p…
EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet
Yitao Yuan, Jianglong Nie, Tianyu Bai +28
In-Network Collective (INC) acceleration holds immense potential for optimizing AI training and inference; however, its cross-layer nature has historically hindered investment and…
Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild
Yue Liu, Ratnadira Widyasari, Yanjie Zhao +3
AI coding assistants are now widely used in software development. Software developers increasingly integrate AI-generated code into their codebases to improve productivity. Prior s…
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
Yunbo Lyu, Jieke Shi, Hong Jin Kang +8
The SZZ algorithm is the dominant technique for identifying bug-inducing commits and underpins many software engineering tasks, such as defect prediction and vulnerability analysis…
An Empirical Study of Speculative Decoding on Software Engineering Tasks
Yijia Li, Junkai Chen, Xing Hu +1
Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. Howeve…
PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing
Huihui Huang, Jieke Shi, Junkai Chen +6
Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with…
Open the Oyster: Empirical Evaluation and Improvement of Code Reasoning Confidence in LLMs
Shufan Wang, Xing Hu, Junkai Chen +2
With the widespread application of large language models (LLMs) in the field of code intelligence, increasing attention has been paid to the reliability and controllability of thei…
Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Chengran Yang, Ting Zhang, Jinfeng Jiang +9
Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis revea…
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
Junkai Chen, Huihui Huang, Yunbo Lyu +10
Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern. Existing benc…
Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
Yikun Li, Ngoc Tan Bui, Ting Zhang +16
Automated vulnerability detection research has made substantial progress, yet its real-world impact remains limited. Prior work found that current vulnerability datasets suffer fro…
Assessing and Advancing Benchmarks for Evaluating Large Language Models in Software Engineering Tasks
Xing Hu, Feifei Niu, Junkai Chen +5
Large language models (LLMs) are gaining increasing popularity in software engineering (SE) due to their unprecedented performance across various applications. These models are inc…
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Martin Weyssow, Chengran Yang, Junkai Chen +12
Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method th…
Understanding Practitioners' Expectations on Clear Code Review Comments
Junkai Chen, Zhenhao Li, Qiheng Mao +3
The code review comment (CRC) is pivotal in the process of modern code review. It provides reviewers with the opportunity to identify potential bugs, offer constructive feedback, a…
NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations
Junkai Chen, Zhenhao Li, Xing Hu +1
Large language models (LLMs) achieve promising results in code generation based on a given natural language description. They have been integrated into open-source projects and com…
Reasoning Runtime Behavior of a Program with LLM: How Far Are We?
Junkai Chen, Zhiyuan Pan, Xing Hu +3
Large language models for code (i.e., code LLMs) have shown strong code understanding and generation capabilities. To evaluate the capabilities of code LLMs in various aspects, man…