Ziqiao Peng - Academic Homepage

Ziqiao Peng 彭子乔

I am a fourth-year PhD candidate at Renmin University of China, supervised by Prof. Jun He from Renmin University of China and Prof. Hongyan Liu from Tsinghua University.

My research focuses on Generative AI and Digital Humans, with a focus on audio-driven talking avatar synthesis, lip synchronization, and real-time interactive avatars.

🎓 I am expected to graduate in June 2027 and actively seeking full-time positions in China and abroad. Feel free to reach out!
我预计于2027年6月毕业，正在寻找国内外全职工作机会，欢迎联系！

Email GitHub ⭐ 2.3k+ Scholar

WeChat

News

2025.11

Journal SyncTalk++ accepted to IEEE TPAMI!

2025.09

Spotlight

OmniSync accepted to NeurIPS 2025 as Spotlight!
Ranked 3rd among all NeurIPS 2025 papers 🏆

2025.09

New MEGADance accepted to NeurIPS 2025!

2025.06

Spotlight GGTalker accepted to ICCV 2025 as Spotlight!

2025.04

New Morpheus accepted to RSS 2025!

2025.03

New DualTalk accepted to CVPR 2025!

2024.02

New SyncTalk accepted to CVPR 2024!

Experience

HeyGen — AI Research Team

Research Intern · Multimodal Video Generation & Real-Time Streaming

Dec 2025 - Present

Tencent — Hunyuan Video Team

Research Intern · Text-Driven Video Action Generation

Jun 2025 - Dec 2025

Kuaishou — Kling GenAI Team

Research Intern · Universal Video Editing for AIGC

Jan 2025 - Jun 2025

Ant Group — Ant Research

Research Intern · Conversational Multi-Character Video Generation

May 2024 - Dec 2024

Pika Labs — Feature Team

Research Intern · Multimodal Video Generation

Jan 2024 - May 2024

Publications

* denotes equal contribution / co-first author

2025
	OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers NeurIPS 2025 Spotlight Ziqiao Peng, Jiwen Liu, Haoxian Zhang, Xiaoqiang Liu, Songlin Tang, Pengfei Wan, Di Zhang, Hongyan Liu, Jun He Project arXiv
	SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting IEEE TPAMI 2025 Ziqiao Peng, Wentao Hu, Junyuan Ma, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Hui Tian, Jun He, Hongyan Liu, Zhaoxin Fan Project arXiv
	DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations CVPR 2025 Ziqiao Peng, Yanbo Fan, Haoyu Wu, Xuan Wang, Hongyan Liu, Jun He, Zhaoxin Fan Project arXiv
	ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars arXiv 2025 Ziqiao Peng, Yi Chen, Yifeng Ma, Guozhen Zhang, Zhiyao Sun, Zixiang Zhou, Youliang Zhang, Zhengguang Zhou, Zhaoxin Fan, Hongyan Liu, Yuan Zhou, Qinglin Lu, Jun He Project arXiv
	MEGADance: Mixture-of-Experts Architecture for Genre-Aware 3D Dance Generation NeurIPS 2025 Kaixing Yang, Xulong Tang, Ziqiao Peng*, Yuxuan Hu, Jun He, Hongyan Liu arXiv
	GGTalker: Talking Head Synthesis with Generalizable Gaussian Priors and Identity-Specific Adaptation ICCV 2025 Spotlight Wentao Hu, Shunkai Li, Ziqiao Peng, Haoxian Zhang, Fan Shi, Xiaoqiang Liu, Pengfei Wan, Di Zhang, Hui Tian Project arXiv
	UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions arXiv 2025 Guozhen Zhang, Zixiang Zhou, Teng Hu, Ziqiao Peng, Youliang Zhang, Yi Chen, Yuan Zhou, Qinglin Lu, Limin Wang Project arXiv
	StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars arXiv 2025 Zhiyao Sun, Ziqiao Peng*, Yifeng Ma, Yi Chen, Zhengguang Zhou, Zixiang Zhou, Guozhen Zhang, Youliang Zhang, Yuan Zhou, Qinglin Lu, Yong-Jin Liu Project arXiv
	Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control RSS 2025 Zongzheng Zhang, Jiawen Yang, Ziqiao Peng, Meng Yang, Jianzhu Ma, Lin Cheng, Huazhe Xu, Hang Zhao, Hao Zhao Code arXiv
	MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation arXiv 2025 Kaixing Yang, Jiashu Zhu, Xulong Tang, Ziqiao Peng**, Xiangyue Zhang, Puwei Wang, Jiahong Wu, Xiangxiang Chu, Hongyan Liu, Jun He Project arXiv
	FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation arXiv 2025 Kaixing Yang, Xulong Tang, Ziqiao Peng*, Xiangyue Zhang, Puwei Wang, Jun He, Hongyan Liu Project arXiv
	CRUISE: Cooperative Reconstruction and Editing in V2X Scenarios using Gaussian Splatting IROS 2025 Haoran Xu, Saining Zhang, Peishuo Li, Baijun Ye, Xiaoxue Chen, Huan-ang Gao, Jv Zheng, Xiaowei Song, Ziqiao Peng, et al. Code
	Meta-Learning Empowered Meta-Face: Personalized Speaking Style Adaptation for Audio-Driven 3D Talking Face Animation ICME 2025 Xukun Zhou, Fengxin Li, Ziqiao Peng, Kejian Wu, Jun He, Biao Qin, Zhaoxin Fan, Hongyan Liu arXiv
2024
	SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis CVPR 2024 Ziqiao Peng, Wentao Hu, Yue Shi, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Jun He, Hongyan Liu, Zhaoxin Fan Project arXiv Code
	VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction arXiv 2024 Haoyu Wu, Ziqiao Peng, Xukun Zhou, Yunfei Cheng, Jun He, Hongyan Liu, Zhaoxin Fan arXiv
	ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement arXiv 2024 Zhefan Rao, Liya Ji, Yazhou Xing, Runtao Liu, Zhaoyang Liu, Jiaxin Xie, Ziqiao Peng, Yingqing He, Qifeng Chen arXiv
2023
	SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces ACM MM 2023 Ziqiao Peng, Yihao Luo, Yue Shi, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan Project arXiv Code
	EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation ICCV 2023 Ziqiao Peng, Haoyu Wu, Zhenbo Song, Hao Xu, Xiangyu Zhu, Hongyan Liu, Jun He, Zhaoxin Fan Project arXiv Code