38 citations · 55 across the 12 of their papers we have counts for
12 papers
Structure-aware Fine-tuning for Code Pre-trained Models
Jiayi Wu, Renyu Zhu, Nuo Chen +3
Over the past few years, we have witnessed remarkable advancements in Code Pre-trained Models (CodePTMs). These models achieved excellent representation capabilities by designing s…
Personalized Programming Guidance based on Deep Programming Learning Style Capturing
Yingfan Liu, Renyu Zhu, Ming Gao
With the rapid development of big data and AI technology, programming is in high demand and has become an essential skill for students. Meanwhile, researchers also focus on boostin…
Exchanging-based Multimodal Fusion with Transformer
Renyu Zhu, Chengcheng Han, Yong Qian +5
We study the problem of multimodal fusion in this paper. Recent exchanging-based methods have been proposed for vision-vision fusion, which aim to exchange embeddings learned from…
Rethinking Noisy Label Learning in Real-world Annotation Scenarios from the Noise-type Perspective
Renyu Zhu, Haoyu Liu, Runze Wu +4
In this paper, we investigate the problem of learning with noisy labels in real-world annotation scenarios, where noise can be categorized into two types: factual noise and ambigui…
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario
Chengcheng Han, Liqing Cui, Renyu Zhu +5
Large pre-trained language models (PLMs) have garnered significant attention for their versatility and potential for solving a wide spectrum of natural language processing (NLP) ta…
Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives
Qiushi Sun, Chengcheng Han, Nuo Chen +4
Large language models (LLMs) have shown increasing power on various natural language processing (NLP) tasks. However, tuning these models for downstream tasks usually needs exorbit…
Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition
Chengcheng Han, Renyu Zhu, Jun Kuang +5
Meta-learning methods have been widely used in few-shot named entity recognition (NER), especially prototype-based methods. However, the Other(O) class is difficult to be represent…
CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure
Nuo Chen, Qiushi Sun, Renyu Zhu +3
Code pre-trained models (CodePTMs) have recently demonstrated significant success in code intelligence. To interpret these models, some probing methods have been applied. However,…
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily
Xiang Li, Renyu Zhu, Yao Cheng +4
We investigate graph neural networks on graphs with heterophily. Some existing methods amplify a node's neighborhood with multi-hop neighbors to include more nodes with homophily.…
A Neural Network Architecture for Program Understanding Inspired by Human Behaviors
Renyu Zhu, Lei Yuan, Xiang Li +2
Program understanding is a fundamental task in program language processing. Despite the success, existing works fail to take human behaviors as reference in understanding programs.…
Programming Knowledge Tracing: A Comprehensive Dataset and A New Model
Renyu Zhu, Dongxiang Zhang, Chengcheng Han +4
In this paper, we study knowledge tracing in the domain of programming education and make two important contributions. First, we harvest and publish so far the most comprehensive d…
On Disambiguating Authors: Collaboration Network Reconstruction in a Bottom-up Manner
Na Li, Renyu Zhu, Xiaoxu Zhou +4
Author disambiguation arises when different authors share the same name, which is a critical task in digital libraries, such as DBLP, CiteULike, CiteSeerX, etc. While the state-of-…