Xingyu Zeng

Shenzhen University — China

Computer Science · Physical Sciences

23h-index3.3kcitations57works0.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(33), Domain Adaptation and Few-Shot Learning(13), Advanced Image and Video Retrieval Techniques(12), Video Surveillance and Tracking Methods(8), Multimodal Machine Learning Applications(8)

Publications57 total

SCALAR: Spatial-concept alignment for robust vision in harsh open world
Pattern Recognition·2026
Performance-guided Reinforced Active Learning for Object Detection
arXiv (Cornell University)·2026Open Access
Performance-guided Reinforced Active Learning for Object Detection
ArXiv.org·2026Open Access
Generative Photographic Control for Scene-Consistent Video Cinematic Editing
arXiv (Cornell University)·2025Open Access
Multi-Modal Semantic Fusion for Smart Contract Vulnerability Detection in Cloud-Based Blockchain Analytics Platforms
Electronics·2025Open Access
Cross-Architecture Binary Code Similarity-Detection Method Based on Contextual Information
Applied Sciences·2025Open Access
GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning
arXiv (Cornell University)·2025Open Access
ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive Search
arXiv (Cornell University)·2025Open Access
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
arXiv (Cornell University)·2025Open Access
Spy Inside: Scalable Verification of Dependable Transformers for Event Time Series Systems
2025
Robustness Verification of Deep Graph Neural Networks Tightened by Linear Approximation
2025· 1 cited
Explainable AI Based Multi-Task Learning Method for Stroke Prognosis
Computers, materials & continua/Computers, materials & continua (Print)·2025Open Access
PUMA: Empowering Unified MLLM with Multi-granular Visual Generation
arXiv (Cornell University)·2024Open Access
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems
2024· 11 citedOpen Access
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems
arXiv (Cornell University)·2023· 7 citedOpen Access
Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection
arXiv (Cornell University)·2023Open Access
TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage
arXiv (Cornell University)·2023· 10 citedOpen Access
An Effective Crop-Paste Pipeline for Few-shot Object Detection
2023· 17 cited
Explore the Power of Synthetic Data on Few-shot Object Detection
2023· 34 cited
Explore the Power of Synthetic Data on Few-shot Object Detection
arXiv (Cornell University)·2023· 3 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Xiaogang Wang(23), Wanli Ouyang(20), Hongsheng Li(10), Kun Wang(8), Rui Zhao(8), Junjie Yan(5), Shaobo Lin(5), Shi Qiu(4), Ping Luo(4), Yonglong Tian(4), Chen Change Loy(4), Xiaoou Tang(4), Tianpeng Bao(4), Tong Xiao(3), Zhe Wang(3), Shuo Yang(3), Zhe Wang(3), Jingqing Ruan(3), Shiwei Shi(3), Hangyu Mao(3)