Haojie Zheng

Haojie zheng

I am currently a Ph.D student at the Camera Intelligence Lab at Peking University, where I work on AI-generated content (AIGC). My PhD advisor is Prof. Boxin Shi.

Previously, I graduated from Hangzhou Dianzi University as a BS in Computer Science and Technology.

Research Works

	InstructAV2AV: Instruction-Guided Audio-Video Joint Editing Haojie Zheng , Yixin Yang , Siqi Yang , Shuchen Weng* , Boxin Shi* arXiv preprint, 2026 arXiv / Project / Code (* Corresponding authors)
	Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner Haojie Zheng † , Shuchen Weng † , Jingqi Liu , Siqi Yang , Boxin Shi ‡ , Xinlong Wang CVPR, 2026 arXiv / Project / Code († Equal contribution ‡ Corresponding authors)
	Audio-Sync Video Generation with Multi-Stream Temporal Control Shuchen Weng † , Haojie Zheng † , Zheng Chang , Si Li , Boxin Shi ‡ , Xinlong Wang ‡ NeurIPS, 2025 Paper / arXiv / Project / Demo / Code († Equal contribution ‡ Corresponding authors)
	VIRES: Video Instance Repainting via Sketch and Text Guided Generation Shuchen Weng † , Haojie Zheng † , Peixuan Zhang , Yuchen Hong , Han Jiang , Si Li , Boxin Shi ‡ CVPR, 2025 Paper / arXiv / Project / Code († Equal contribution ‡ Corresponding authors)
	OpenCIR: Conditional Image Repainting with Open Condition Mixture Shuchen Weng † , Xiaocheng Gong † , Haojie Zheng † , Xinlong Wang , Si Li ‡ , Boxin Shi TPAMI, 2025 Paper / Project († Equal contribution ‡ Corresponding authors)

Last updated: Nov. 2024
Web page design credit to Jon Barron