Zunnan Xu

Zunnan Xu

PhD StudentMMLab@NTU

Hi, I am a Ph.D. student at the MMLab at NTU. My research focuses on multimodal learning and generative AI, aiming to build a unified perception-reasoning-action engine to interact with the physical world. Prior to NTU, I was a Research Scientist at X Square Robot, working on VLA and world action models. I received my degree from Tsinghua University and interned in the Multimodal Group at Tencent Hunyuan, focusing on video generation.

News

  • [2026]  -  Recognized as a Top Reviewer by NeurIPS 2026.
  • [2026]  -  One paper accepted to NeurIPS 2026.
  • [2026]  -  Two papers accepted to ACL 2026 and ICML 2026.
  • [2025]  -  Received Outstanding Reviewer Award at Machine Intelligence Research.
  • [2025]  -  Three papers accepted to NeurIPS 2025 and ICCV 2025.
  • [2025]  -  Received Outstanding Reviewer Award at CVPR 2025.
  • [2025]  -  Three papers accepted to CVPR 2025.
  • [2024]  -  One paper accepted to EMNLP 2024.
  • [2024]  -  Won 3rd prize in CVPR 2024 OVD challenge.
  • [2024]  -  Two papers accepted to ICML 2024 workshop.
  • [2024]  -  One paper accepted to NeurIPS 2024.
  • [2023]  -  One paper accepted to ICCV 2023.

Selected Publications

* denotes equal contribution

HunyuanPortrait: Implicit condition control for enhanced portrait animation

Zunnan Xu, Zhentao Yu, Zixiang Zhou, et al.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
PDF Code Home

Igniting vlms toward the embodied space

Zunnan Xu (Core contributor, shown as Zach Xu) and X Square Robot Team
Technical Report, 2025
PDF Code Home

HunyuanVideo: A Systematic Framework For Large Video Generative Models

Zunnan Xu (Core contributor) and Hunyuan Foundation Model Team
Technical Report, 2024
PDF Code Home

Bridging vision and language encoders: Parameter-efficient tuning for referring image segmentation

Zunnan Xu, Zhihong Chen, Yong Zhang, Yibing Song, Xiang Wan, Guanbin Li
IEEE/CVF International Conference on Computer Vision (ICCV), 2023
PDF Code Home

Enhancing Fine-grained Multi-modal Alignment via Adapters: A Parameter-Efficient Training Framework

Zunnan Xu, Jiaqi Huang, Ting Liu, et al.
International Conference on Machine Learning (ICML), 2024
PDF Code Home

Mambatalk: Efficient holistic gesture synthesis with selective state space models

Zunnan Xu, Yukang Lin, Haonan Han, et al.
Conference on Neural Information Processing Systems (NeurIPS), 2024
PDF Code Home

Chain of generation: Multi-modal gesture synthesis via cascaded conditional control

Zunnan Xu, Yachao Zhang, Sicheng Yang, Ronghui Li, Xiu Li
AAAI Conference on Artificial Intelligence (AAAI), 2024
PDF Code Home

SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning

Jiaqi Huang*, Zunnan Xu*, Jun Zhou, et al.
Conference on Neural Information Processing Systems (NeurIPS), 2025
PDF Code Home

Densely Connected Parameter-Efficient Tuning for Referring Image Segmentation

Jiaqi Huang*, Zunnan Xu*, Ting Liu, et al.
AAAI Conference on Artificial Intelligence (AAAI), 2025
PDF Code Home

Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation

Xiaoyu Jin*, Zunnan Xu*, Mingwen Ou, Wenming Yang
International Conference on Machine Learning (ICML), 2024
PDF Code Home

MaPPER: Multimodal Prior-guided Parameter Efficient Tuning for Referring Expression Comprehension

Ting Liu*, Zunnan Xu*, Yue Hu, Liangtao Shi, Zhiqiang Wang, Quanjun Yin
Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024
PDF Code Home

Zero-shot 3D-Aware Trajectory-Guided image-to-video generation via Test-Time Training

Ruicheng Zhang*, Jun Zhou*, Zunnan Xu*, et al.
AAAI Conference on Artificial Intelligence (AAAI), 2026
PDF Code Home

Separate to Collaborate: Dual-Stream Diffusion Model for Coordinated Piano Hand Motion Synthesis

Zihao Liu*, Mingwen Ou*, Zunnan Xu*, et al.
ACM International Conference on Multimedia (MM), 2025
PDF Code Home

Academic Services

Conference Reviewer

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • IEEE/CVF International Conference on Computer Vision (ICCV)
  • ACM SIGGRAPH Conference on Computer Graphics and Interactive Techniques (SIGGRAPH)
  • Conference on Neural Information Processing Systems (NeurIPS)
  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)
  • Annual Meeting of the Association for Computational Linguistics (ACL)

Journal Reviewer

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Image Processing (TIP)
  • International Journal of Computer Vision (IJCV)
  • Transactions on Machine Learning Research (TMLR)
  • Machine Intelligence Research (MIR)