高正｜梧州学院｜学者主页

2026

Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features

Zheng Gao, Debin Meng, Yunqi Miao, Zhensong Zhang, Songcen Xu, Ioannis Patras, Jifei Song

arXiv preprint

2026

TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories

Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang, Yang Song, Yulei Sui, Zhenchang Xing, Liming Zhu

arXiv preprint

2026

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

arXiv preprint

2026

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

Rui Bao, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Yang Song, Jiaojiao Jiang

arXiv preprint

2026

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

Zheng Gao, Yifan Yang, Xiaoyu Li, Xiaoyan Feng, Haoran Fan, Yang Song, Jiaojiao Jiang

arXiv preprint

2026

The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion

Xiaoyu Li, Zheng Gao, Chiwun Yang, Zhizhou Sha

arXiv preprint

2026

Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering

Zheng Gao, Xiaoyu Li, Zhicheng Bao, Jiaojiao Jiang

arXiv preprint

2026

TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

arXiv preprint

2026

Watermark Forensics for Generative Models: An Information-Theoretic Perspective

Xiaoyu Li, Zheng Gao, Xiaoyan Feng, Jiaojiao Jiang, Yulei Sui, Jiankun Hu

arXiv preprint

2026

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

arXiv preprint

DOI

2026

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

Xiaoyan Feng, Zheng Gao, Tong Guan, Rui Bao, Bokang Zeng, Xiaoyu Li, Jiaojiao Jiang

arXiv preprint

2026

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

Xiaoyu Li, Andi Han, Dai Shi, Zheng Gao, Jiaojiao Jiang, Junbin Gao

arXiv preprint

2026

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search

Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang

arXiv preprint

2026

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

Yifan Yang, Zhaoyan Wang, Zheng Gao, Xiaoyu Li, Jiaojiao Jiang

arXiv preprint

2025

Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement

Zhaoyan Wang, Zheng Gao, Arogya Kharel, In-Young Ko

arXiv preprint

2025

BondBERT: What we learn when assigning sentiment in the bond market

Toby Barter, Zheng Gao, Eva Christodoulaki, Jing Chen, John Cartlidge

arXiv preprint

DOI

2025

TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization

Debin Meng, Chen Jin, Zheng Gao, Yanran Li, Ioannis Patras, Georgios Tzimiropoulos

arXiv preprint

2024

Self-Supervised Facial Representation Learning with Facial Region Awareness

Zheng Gao, Ioannis Patras

arXiv preprint

2023

Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features

Zheng Gao, Chen Feng, Ioannis Patras

arXiv preprint

2022

Detection of Sparse Anomalies in High-Dimensional Network Telescope Signals

Rafail Kartsioukas, Rajat Tandon, Zheng Gao, Jelena Mirkovic, Michalis Kallitsis, Stilian Stoev

arXiv preprint

2021

Improving Community Detection Performance in Heterogeneous Music Network by Learning Edge-type Usefulness Distribution

Zheng Gao, Chun Guo, Shutian Ma, Xiaozhong Liu

arXiv preprint

2021

Two-stage Voice Application Recommender System for Unhandled Utterances in Intelligent Personal Assistant

Wei Xiao, Qian Hu, Thahir Mohamed, Zheng Gao, Xibin Gao, Radhika Arava, Mohamed AbdelHady

arXiv preprint

2020

Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

Zheng Gao, Hongsong Li, Zhuoren Jiang, Xiaozhong Liu

arXiv preprint

DOI

2020

Efficient Personalized Community Detection via Genetic Evolution

Zheng Gao, Chun Guo, Xiaozhong Liu

arXiv preprint

DOI

2020

Typilus: Neural Type Hints

Miltiadis Allamanis, Earl T. Barr, Soline Ducousso, Zheng Gao

arXiv preprint

DOI

2019

Neural Related Work Summarization with a Joint Context-driven Attention Mechanism

Yongzhen Wang, Xiaozhong Liu, Zheng Gao

arXiv preprint

DOI

2019

AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data

Zheng Gao, Lin Guo, Chi Ma, Xiao Ma, Kai Sun, Hang Xiang, Xiaoqiang Zhu, Hongsong Li, Xiaozhong Liu

arXiv preprint

2018

edge2vec: Representation learning using edge semantics for biomedical knowledge discovery

Zheng Gao, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner, Brian Foote, David Wild, Qi Yu, Ying Ding

arXiv preprint

2018

Mathematics Content Understanding for Cyberlearning via Formula Evolution Map

Zhuoren Jiang, Liangcai Gao, Ke Yuan, Zheng Gao, Zhi Tang, Xiaozhong Liu

arXiv preprint

高正

精选作品

期刊论文

Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic Injection

Science out of its Ivory Tower: improving accessibility with reinforcement learning

VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond

Polarization spatial and semantic learning lightweight network for underwater salient object detection

Object phase-valid region segmentation method for FPP-based three-dimensional measurement.

Lightweight dual-domain token learning method for hyperspectral image classification

预印本

Diffusion-Based Makeup Transfer with Facial Region-Aware Makeup Features

TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories

SHIFT: Stochastic Hidden-Trajectory Deflection for Removing Diffusion-based Watermark

DRIFT: Removing Diffusion Watermarks by Deflecting the Generative Trajectory

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

The Singularity Has a Distribution: Exact Timing Laws and Detection Limits for a Stochastic Intelligence Explosion

Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering

TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories

Watermark Forensics for Generative Models: An Information-Theoretic Perspective

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion Images

Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics via the Lens of Language Generation in the Limit

RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search

CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement

BondBERT: What we learn when assigning sentiment in the bond market

TPSO: Training-Free Diverse Image Generation via Semantic Prompt Embedding Optimization

Self-Supervised Facial Representation Learning with Facial Region Awareness

Self-Supervised Representation Learning with Cross-Context Learning between Global and Hypercolumn Features

Detection of Sparse Anomalies in High-Dimensional Network Telescope Signals

Improving Community Detection Performance in Heterogeneous Music Network by Learning Edge-type Usefulness Distribution

Two-stage Voice Application Recommender System for Unhandled Utterances in Intelligent Personal Assistant

Detecting User Community in Sparse Domain via Cross-Graph Pairwise Learning

Efficient Personalized Community Detection via Genetic Evolution

Typilus: Neural Type Hints

Neural Related Work Summarization with a Joint Context-driven Attention Mechanism

AMAD: Adversarial Multiscale Anomaly Detection on High-Dimensional and Time-Evolving Categorical Data

edge2vec: Representation learning using edge semantics for biomedical knowledge discovery

Mathematics Content Understanding for Cyberlearning via Formula Evolution Map