Zhao, Canyu
- MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
2024/07/23 by Canyu Zhao, Zhao, Canyu, Mingyu Liu +13 · 26 citations
Computer Science · #Advanced Vision and Imaging #Video Analysis and Summarization #Computer Graphics and Visualization Techniques
- FreeCustom: Tuning-Free Customized Image Generation for Multi-Concept Composition
2024/05/22 by Ganggui Ding, Ding, Ganggui, Canyu Zhao +11 · 11 citations
Computer Science · Engineering · #Advanced Image and Video Retrieval Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #Image Retrieval and Classification Techniques
- DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
2025/02/24 by Canyu Zhao, Zhao, Canyu, Yanlong Sun +15 · 3 voices · 11 citations
#cs.CV
- AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort
2023/11/19 by Wen Wang, Wang, Wen, Canyu Zhao +9 · 7 citations
Computer Science · #Video Analysis and Summarization #Multimodal Machine Learning Applications #Advanced Image and Video Retrieval Techniques
- Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
2025/05/27 by Zhu, Muzhi, Zhong, Hao, Zhao, Canyu +8 · 17 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
- Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration
2025/05/26 by Hao Zhong, Zhong, Hao, Muzhi Zhu +14 · 12 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation #Semantic Web and Ontologies
- Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization
2025/08/20 by Canyu Zhao, Xiaoman Li, Zhao, Canyu +8 · 2 citations
Computer Science · Engineering · #Computer Graphics and Visualization Techniques #Additive Manufacturing and 3D Printing Technologies