42 citations · 94 across the 32 of their papers we have counts for
32 papers
TRACE: Trajectory Representation and Consistency Estimation for AI-Generated Video Detection
Huangsen Cao, Hongkang chu, Siyao Yu +3
Recent advances in generative video models have enabled the synthesis of visually realistic content, posing significant challenges to synthetic video detection. Existing detectors…
ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection
Huangsen Cao, Hongkang Chu, Yuxi Li +6
The rapid advancement of generative models has made synthetic images increasingly realistic, challenging reliable detection. Existing methods are often limited to end-to-end classi…
Graph Topology Information Enhanced Heterogeneous Graph Representation Learning
He Zhao, Zhiwei Zeng, Yongwei Wang +1
Real-world heterogeneous graphs are inherently noisy and usually not in the optimal graph structures for downstream tasks, which often adversely affects the performance of GRL mode…
Enhancing Diffusion-Based Quantitatively Controllable Image Generation via Matrix-Form EDM and Adaptive Vicinal Training
Xin Ding, Yun Chen, Sen Zhang +5
Continuous Conditional Diffusion Model (CCDM) is a diffusion-based framework designed to generate high-quality images conditioned on continuous regression labels. Although CCDM has…
PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning
Langming Liu, Kangtao Lv, Haibin Chen +8
Large language models (LLMs), despite their powerful capabilities, suffer from factual hallucinations where they generate verifiable falsehoods. We identify a root of this issue: t…
Data Distribution Matters: A Data-Centric Perspective on Context Compression for Large Language Model
Kangtao Lv, Jiwei Tang, Langming Liu +7
The deployment of Large Language Models (LLMs) in long-context scenarios is hindered by computational inefficiency and significant information redundancy. Although recent advanceme…
REVEAL: Reasoning-Enhanced Forensic Evidence Analysis for Explainable AI-Generated Image Detection
Huangsen Cao, Qin Mei, Zhiheng Li +9
The rapid progress of visual generative models has made AI-generated images increasingly difficult to distinguish from authentic ones, posing growing risks to social trust and info…
Latent Danger Zone: Distilling Unified Attention for Cross-Architecture Black-box Attacks
Yang Li, Chenyu Wang, Tingrui Wang +4
Black-box adversarial attacks remain challenging due to limited access to model internals. Existing methods often depend on specific network architectures or require numerous queri…
How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models
Kangtao Lv, Haibin Chen, Yujin Yuan +5
Large language models (LLMs) have attracted significant attention due to their impressive general capabilities across diverse downstream tasks. However, without domain-specific opt…
Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
Xin Ding, Yun Chen, Yongwei Wang +4
Recent advances in continuous conditional generative modeling, including Continuous conditional Generative Adversarial Network (CcGAN) and Continuous Conditional Diffusion Model (C…
NAN: A Training-Free Solution to Coefficient Estimation in Model Merging
Chongjie Si, Kangtao Lv, Jingjing Jiang +6
Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existin…
Training-free LLM-generated Text Detection by Mining Token Probability Sequences
Yihuai Xu, Yongwei Wang, Yifei Bi +4
Large language models (LLMs) have demonstrated remarkable capabilities in generating high-quality texts across diverse domains. However, the potential misuse of LLMs has raised sig…
HyperDet: Generalizable Detection of Synthesized Images by Generating and Merging A Mixture of Hyper LoRAs
Huangsen Cao, Yongwei Wang, Yinfeng Liu +6
The emergence of diverse generative vision models has recently enabled the synthesis of visually realistic images, underscoring the critical need for effectively detecting these ge…
Hyper Adversarial Tuning for Boosting Adversarial Robustness of Pretrained Large Vision Models
Kangtao Lv, Huangsen Cao, Kainan Tu +4
Large vision models have been found vulnerable to adversarial examples, emphasizing the need for enhancing their adversarial robustness. While adversarial training is an effective…
DeMuVGN: Effective Software Defect Prediction Model by Learning Multi-view Software Dependency via Graph Neural Networks
Yu Qiao, Lina Gong, Yu Zhao +2
Software defect prediction (SDP) aims to identify high-risk defect modules in software development, optimizing resource allocation. While previous studies show that dependency netw…
Coding-PTMs: How to Find Optimal Code Pre-trained Models for Code Embedding in Vulnerability Detection?
Yu Zhao, Lina Gong, Zhiqiu Huang +3
Vulnerability detection is garnering increasing attention in software engineering, since code vulnerabilities possibly pose significant security. Recently, reusing various code pre…
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models
Renqiu Xia, Song Mao, Xiangchao Yan +19
Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data. Leveraging multi-modality data extracted from these docum…
CCDM: Continuous Conditional Diffusion Models for Image Generation
Xin Ding, Yongwei Wang, Kao Zhang +1
Continuous Conditional Generative Modeling (CCGM) estimates high-dimensional data distributions, such as images, conditioned on scalar continuous variables (aka regression labels).…
Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Jingke Zhao, Zan Wang, Yongwei Wang +1
Backdoor attacks have been shown to impose severe threats to real security-critical scenarios. Although previous works can achieve high attack success rates, they either require ac…
HGAttack: Transferable Heterogeneous Graph Adversarial Attack
He Zhao, Zhiwei Zeng, Yongwei Wang +2
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is…
Turning Waste into Wealth: Leveraging Low-Quality Samples for Enhancing Continuous Conditional Generative Adversarial Networks
Xin Ding, Yongwei Wang, Zuheng Xu
Continuous Conditional Generative Adversarial Networks (CcGANs) enable generative modeling conditional on continuous scalar variables (termed regression labels). However, they can…
Occlusion-Robust FAU Recognition by Mining Latent Space of Masked Autoencoders
Minyang Jiang, Yongwei Wang, Martin J. McKeown +1
Facial action units (FAUs) are critical for fine-grained facial expression analysis. Although FAU detection has been actively studied using ideally high quality images, it was not…
DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
Zheqi Lv, Wenqiao Zhang, Shengyu Zhang +8
Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of…
Revisiting Item Promotion in GNN-based Collaborative Filtering: A Masked Targeted Topological Attack Perspective
Yongwei Wang, Yong Liu, Zhiqi Shen
Graph neural networks (GNN) based collaborative filtering (CF) have attracted increasing attention in e-commerce and social media platforms. However, there still lack efforts to ev…