50 citations · 70 across the 13 of their papers we have counts for
14 papers
CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
Yuchen Liu, Zongzhen Yang, Binhang Qi +2
Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining. However, para…
Generalizing Test Cases for Comprehensive Test Scenario Coverage
Binhang Qi, Yun Lin, Xinyi Weng +4
Test cases are essential for software development and maintenance. In practice, developers derive multiple test cases from an implicit pattern based on their understanding of requi…
Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction
Chenyan Liu, Yun Lin, Yuhuan Huang +5
In industrial and open-source software engineering tasks, developers often perform project-wise code editing tasks, including feature enhancement, refactoring, and bug fixing, wher…
EditFlow: Benchmarking and Optimizing Code Edit Recommendation Systems via Reconstruction of Developer Flows
Chenyan Liu, Yun Lin, Jiaxin Chang +5
Large language models (LLMs) for code editing have achieved remarkable progress, yet recent empirical studies reveal a fundamental disconnect between technical accuracy and develop…
NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
Xiaohan Bi, Binhang Qi, Hailong Sun +3
With the growing incorporation of deep neural network (DNN) models into modern software systems, the prohibitive construction costs have become a significant challenge. Model reuse…
Generating Project-Specific Test Cases with Requirement Validation Intention
Binhang Qi, Yun Lin, Xinyi Weng +5
Test cases are valuable assets for maintaining software quality. State-of-the-art automated test generation techniques typically focus on maximizing program branch coverage or tran…
CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
Zongzhen Yang, Binhang Qi, Hailong Sun +3
Model merging based on task vectors, i.e., the parameter differences between fine-tuned models and a shared base model, provides an efficient way to integrate multiple task-specifi…
Clustering Properties of Self-Supervised Learning
Xi Weng, Jianing An, Xudong Ma +5
Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering prop…
Aegis:An Advanced LLM-Based Multi-Agent for Intelligent Functional Safety Engineering
Lu Shi, Bin Qi, Jiarui Luo +5
Functional safety is a critical aspect of automotive engineering, encompassing all phases of a vehicle's lifecycle, including design, development, production, operation, and decomm…
Reusing Convolutional Neural Network Models through Modularization and Composition
Binhang Qi, Hailong Sun, Hongyu Zhang +1
With the widespread success of deep learning technologies, many trained deep neural network (DNN) models are now publicly available. However, directly reusing the public DNN models…
Modularizing while Training: A New Paradigm for Modularizing DNN Models
Binhang Qi, Hailong Sun, Hongyu Zhang +2
Deep neural network (DNN) models have become increasingly crucial components in intelligent software systems. However, training a DNN model is typically expensive in terms of both…
Reusing Deep Neural Network Models through Model Re-engineering
Binhang Qi, Hailong Sun, Xiang Gao +3
Training deep neural network (DNN) models, which has become an important task in today's software development, is often costly in terms of computational resources and time. With th…
Patching Weak Convolutional Neural Network Models through Modularization and Composition
Binhang Qi, Hailong Sun, Xiang Gao +1
Despite great success in many applications, deep neural networks are not always robust in practice. For instance, a convolutional neuron network (CNN) model for classification task…
HCIC: Hardware-assisted Control-flow Integrity Checking
Jiliang Zhang, Binhang Qi, Gang Qu
Recently, code reuse attacks (CRAs), such as return-oriented programming (ROP) and jump-oriented programming (JOP), have emerged as a new class of ingenious security threatens. Att…