42 citations · 123 across the 10 of their papers we have counts for
10 papers
How to Select Pre-Trained Code Models for Reuse? A Learning Perspective
Zhangqian Bi, Yao Wan, Zhaoyang Chu +5
Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, cod…
Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study
Yang Wu, Yao Wan, Hongyu Zhang +5
The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insight…
Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation
Zhaoyang Chu, Yao Wan, Qian Li +5
Vulnerability detection is crucial for ensuring the security and reliability of software systems. Recently, Graph Neural Networks (GNNs) have emerged as a prominent code embedding…
CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code
Batu Guan, Yao Wan, Zhangqian Bi +4
Large Language Models (LLMs) have achieved remarkable progress in code generation. It now becomes crucial to identify whether the code is AI-generated and to determine the specific…
Does Your Neural Code Completion Model Use My Code? A Membership Inference Approach
Yao Wan, Guanghua Wan, Shijie Zhang +4
Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Although using source code in GitHub has been a common prac…
Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit
Yao Wan, Yang He, Zhangqian Bi +6
Code intelligence leverages machine learning techniques to extract knowledge from extensive code corpora, with the aim of developing intelligent tools to improve the quality and pr…
Rethinking the Video Sampling and Reasoning Strategies for Temporal Sentence Grounding
Jiahao Zhu, Daizong Liu, Pan Zhou +8
Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a spars…
Cross-Language Binary-Source Code Matching with Intermediate Representations
Yi Gui, Yao Wan, Hongyu Zhang +5
Binary-source code matching plays an important role in many security and software engineering related tasks such as malware detection, reverse engineering and vulnerability assessm…
FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization
Dezhong Yao, Wanning Pan, Michael J O'Neill +4
One underlying assumption of recent federated learning (FL) paradigms is that all local models usually share the same network architecture and size, which becomes impractical for d…
Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data
Dezhong Yao, Wanning Pan, Yutong Dai +5
Federated learning enables multiple clients to collaboratively learn a global model by periodically aggregating the clients' models without transferring the local data. However, du…