Junshu Tang (唐俊姝)

I am currently a senior researcher at Tencent Hunyuan Team. I obtained my PhD degree at the Shanghai Jiao Tong University (SJTU), advised by Lizhuang Ma.
Before that, I was a research intern at Tencent Youtu Lab. In 2023, I was a research intern at OpenMMLab, Shanghai AI Lab, working with Yanhong Zeng and Bo Dai.
From 2021 to 2023, I was a research intern at Visual Computing Group, Microsoft Research Asia (MSRA), working with Bo Zhang and Dong Chen.
I'm interested in 2D video / 3D scene content generation, mainly focus on Video-based World Model, and Action Models.

Email / Github / Google Scholar / Twitter

News

News (Oct 2026): We release Hy-Nomas, an open-source free-form interactive world generation model.
News (Sep 2026): Two papers are accepted to NeurIPS 2026.
News (Dec 2024): Two papers are accepted to AAAI 2025.
News (Aug 2024): TexDreamer is accepted to ECCV 2024 as Oral.
News (Jul 2024): Two papers are accepted to ECCV 2024.
News (Feb 2024): One paper is accepted to CVPR 2024.
News (Sep 2023): One paper is accepted to TVCG 2023.
News (Jul 2023): One paper is accepted to ICCV 2023.
News (Jul 2023): One paper is accepted to CAD/Graphics 2023.
News (Mar 2022): One paper is accepted to CVPR 2022.
News (Apr 2021): One paper is accepted to TIP 2021.
News (Feb 2021): One paper is accepted to IEEE Multimedia 2021.
News (Mar 2020): One paper is accepted to ICME 2020 as Oral presentation.

Publications

(*equal contribution, ^intern)

	Hy-Nomas: Towards Free-Form Interactive World Generation Tencent Hy Visual Generation Team (Core Contributor) Technical Report, 2026 project page / paper / code / model / demo
	EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World Models Xiaokun Feng^, Junshu Tang, Zeyi Lin, Ling-Hao Chen, Shuai Shao, Qinglin Lu, Kaiqi Huang NeurIPS, 2026 project page / paper / code / dataset
	WorldReward: Reward Modeling for Camera-Conditioned World Models Yibin Wang, Zehan Wang, Junshu Tang, Zhimin Li, Yujie Zhou, Jiazi Bu, Pengyang Ling, Feng Han, Zhixiong Zhang, Long Xing, Shengyuan Ding, Ziang Li, Cheng Jin, Yuhang Zang, Jiaqi Wang, Tianyu Pang arXiv, 2026 project page / paper / code / benchmark
	Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model Junshu Tang, Jiacheng Liu^, Jiaqi Li^, Longhuang Wu, Haoyu Yang, Penghao Zhao, Siruis Gong, Xiang Yuan, Shuai Shao, Linfeng Zhang, Qinglin Lu Technical Report*, 2025 project page / paper / demo
	Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition Jiaqi Li^, Junshu Tang, Zhiyong Xu, Longhuang Wu, Yuan Zhou, Shuai Shao, Tianbao Yu, Zhiguo Cao, Qinglin Lu Technical Report, 2025 project page / paper / code
	Hunyuan-Game: Industrial-grade Intelligent Game Creation Model Hunyuan MultiModal Model Team (Core Contributor) Technical Report, 2025 project page / paper
	HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters Yi Chen, Sen Liang, Zixiang Zhou, Ziyao Huang, Yifeng Ma, Junshu Tang, Qin Lin, Yuan Zhou, Qinglin Lu Technical Report, 2025 project page / paper / code / demo
	ClotheDreamer: Text-Guided Garment Generation with 3D Gaussians Yufei Liu, Junshu Tang, Chu Zheng, Shijie Zhang, Jinkun Hao, Junwei Zhu, Dongjin Huang arXiv, 2024 project page / paper / code
	Portrait3D: 3D Head Generation from Single In-the-wild Portrait Image Jinkun Hao, Junshu Tang, Jiangning Zhang, Ran Yi, Yijia Hong, Moran Li, Weijian Cao, Yating Wang, Lizhuang Ma AAAI, 2025 project page / paper / code
	FastLGS: Speeding up Language Embedded Gaussians with Feature Grid Mapping Yuzhou Ji, He Zhu, Junshu Tang, Wuyi Liu, Zhizhong Zhang, Yuan Xie, Lizhuang Ma, Xin Tan AAAI, 2025 project page / paper
	FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis Ke Fan, Junshu Tang, Weijian Cao, Ran Yi, Moran Li, Jingyu Gong, Jiangning Zhang, Yabiao Wang, Chengjie Wang, Lizhuang Ma ECCV, 2024 project page / paper / code
	TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation Yufei Liu, Junwei Zhu, Junshu Tang, Shijie Zhang, Jiangning Zhang, Weijian Cao, Chengjie Wang, Yunsheng Wu, Dongjin Huang ECCV, 2024, Oral project page / paper / code
	Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text Junshu Tang , Yanhong Zeng, Ke Fan, Xuheng Wang, Bo Dai, Kai Chen, Lizhuang Ma CVPR, 2024 project page / paper / code
	Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior Junshu Tang , Tengfei Wang, Bo Zhang, Ting Zhang, Ran Yi, Lizhuang Ma, Dong Chen ICCV, 2023 project page / paper / code
	3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation Junshu Tang , Bo Zhang , Binxin Yang , Ting Zhang , Dong Chen , Lizhuang Ma , Fang Wen TVCG, 2023 project page / paper / code
	Prototype-Aware Heterogeneous Task for Point Cloud Completion Junshu Tang , Jiachen Xu, Jingyu Gong, Haichuan Song, Yuan Xie, Lizhuang Ma CAD/Graphics , 2023 paper
	LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints Junshu Tang , Zhijun Gong, Ran Yi, Yuan Xie, Lizhuang Ma CVPR, 2022 paper / code
	Explicit facial expression transfer via fine-grained semantic representations Zhiwen Shao, Hengliang Zhu, Junshu Tang , Xuequan Lu, and Lizhuang Ma TIP , 2021 paper
	Fine-grained expression manipulation via structured latent space. Junshu Tang , Zhiwen Shao, Lizhuang Ma ICME Oral Presentation, 2020 paper / code