武宇｜武汉大学｜学者主页

期刊论文

2026

从数据表征到自动化发现：AI驱动的化学研究新范式

武宇，肖帆，朱智慧

《计算》

2026

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation Without Information Leakage

Tianchen Zeng, Sai Wang, Yu Wu, Bo Du

IEEE Transactions on Image Processing

DOI

2026

TV-Dialogue: Crafting Theme-Aware Video Dialogues by Decoupling Global Planning and Local Execution

Sai Wang, Fan Ma, Xinyi Li, Yutian Lin, Bo Du, Yu Wu

IEEE Transactions on Multimedia

DOI

2025

Forecasting when to forecast: Accelerating diffusion models with confidence-gated taylor

Xiaoliu Guan, Lielin Jiang, Hanqi Chen, Xu Zhang, Xu Zhang, Jiaxing Yan, Guanzhong Wang, Yi Liu, Zetao Zhang, Yu Wu

Knowledge-Based Systems

DOI

2025

Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation

Feizhen Huang, Yu Wu, Yutian Lin, Bo Du

International Joint Conference on Artificial Intelligence

DOI

2025

Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model

Yingying Fan, Qiong Yang, Kaisiyuan Wang, Hang Zhou, Yingying Li, Haocheng Feng, Errui Ding, Yu Wu, Jingdong Wang

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2025

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

Wei Chen, Li Lin, Yongqi Yang, Bin Wen, Fan Yang, Tingting Gao, Yu Wu, Long Chen

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2025

RQTalker: Speech-driven 3D Facial Animation via Region-aware Vector Quantization

Yingying Fan, Kaisiyuan Wang, Hang Zhou, Shengyi He, Yu Wu

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2024

An Efficient and Effective Transformer Decoder-Based Framework for Multi-task Visual Grounding

Wei Chen, Long Chen, Yu Wu

Lecture notes in computer science

DOI

2024

A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges

Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, Yi Yang

Vicinagearth.

DOI

2024

Iterative Ensemble Training with Anti-gradient Control for Mitigating Memorization in Diffusion Models

Xiao Liu, Xiaoliu Guan, Yu Wu, Jiaxu Miao

Lecture notes in computer science

DOI

2024

Vision + X: A Survey on Multimodal Learning in the Light of Data

Ye Zhu, Yu Wu, Nicu Sebe, Yan Yan

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2023

Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World

Qifan Yu, Juncheng Li, Yu Wu, Siliang Tang, Wei Ji, Yueting Zhuang

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2023

Learning to Segment Every Referring Object Point by Point

Mengxue Qu, Yu Wu, Yunchao Wei, Wu Liu, Xiaodan Liang, Yao Zhao

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

预印本

2023

A Sampling-Based Domain Generalization Study with Diffusion Generative Models

Ye Zhu, Yu Wu, Duo Xu, Zhiwei Deng, Yan Yan, Olga Russakovsky

arXiv (Cornell University)

DOI

2022

Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation

Ye Zhu, Yu Wu, Kyle Olszewski, Jian Ren, Sergey Tulyakov, Yan Yan

arXiv (Cornell University)

DOI

武宇

精选作品

期刊论文

从数据表征到自动化发现：AI驱动的化学研究新范式

DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation Without Information Leakage

TV-Dialogue: Crafting Theme-Aware Video Dialogues by Decoupling Global Planning and Local Execution

Forecasting when to forecast: Accelerating diffusion models with confidence-gated taylor

Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation

Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model

CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation

RQTalker: Speech-driven 3D Facial Animation via Region-aware Vector Quantization

An Efficient and Effective Transformer Decoder-Based Framework for Multi-task Visual Grounding

A survey on LLM-based multi-agent systems: workflow, infrastructure, and challenges

Iterative Ensemble Training with Anti-gradient Control for Mitigating Memorization in Diffusion Models

Vision + X: A Survey on Multimodal Learning in the Light of Data

Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World

Learning to Segment Every Referring Object Point by Point

预印本

A Sampling-Based Domain Generalization Study with Diffusion Generative Models

Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation

研究方向