I’m a PhD candidate at University of California, Santa Cruz, advised by professor James Davis.

I have been a research intern at Snap Research, mentored by Peter Wonka, Jian Wang, and Hsin-Ying Lee, and at ByteDance, mentored by Chengjiang Long. At Snap, I worked on 3D/4D generation, structured motion and state representations, cross-embodiment control, and generative simulation. At ByteDance, I worked on human-centric world modeling, including expressive human-state representations, feed-forward 3D perception, synthetic data generation, and real-time state estimation from multimodal and partial observations.

I received my Bachelor degree of Electronic Engineering at Beijing University of Posts and Telecommunications.

Research interests

3D/4D representation learning, generative modeling, and human-centric world models, with particular interests in dynamic state representation, motion modeling, and controllable simulation.

Selected Publications

RegHead: Non-Humanoid Head Blendshapes via Feed-Forward Registration
Jiahao Luo, Hao Zhang, Jianqi Chen, Yijie He, Jiaxu Zou, Michael Vasilkovsky, Sergei Korolev, Sergey Tulyakov, Chaoyang Wang, Peter Wonka, James Davis, Jian Wang
ECCV 2026
[Paper]

RigMo: Unifying Rig and Motion Learning for Generative Animation
Hao Zhang, Jiahao Luo, Bohui Wan, Yizhou Zhao, Zongrui Li, Michael Vasilkovsky, Chaoyang Wang, Jian Wang, Narendra Ahuja, Bing Zhou
CVPR 2026
[Paper]

T2Bs: Text-to-Character Blendshapes via Video Generation
Jiahao Luo, Chaoyang Wang, Michael Vasilkovsky, Vladislav Shakhrai, Di Liu, Peiye Zhuang, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee, James Davis, Jian Wang
ICCV 2025
[Paper]

FFAvatar:Few-Shot, Feedforward, and Generalizable Avatar Reconstruction
Thuan Hoang Nguyen, Jiahao Luo, Yinyu Nie, Haoyang Wang, George Papandreou, Hao Li, Jian Wang, Gordon Guocheng Qian
[Paper]

Snapmoji: Instant Generation of Animatable Dual-Stylized Avatars
Eric Ming Chen, Di Liu, Sizhuo Ma, Michael Vasilkovsky, Bing Zhou, Qiang Gao, Wenzhou Wang, Jiahao Luo, Dimitris N. Metaxas, Vincent Sitzmann, Jian Wang
WACV 2026
[Paper]

SplatFace: Gaussian Splat Face Reconstruction Leveraging an Optimizable Surface
Jiahao Luo, Jing Liu, James Davis
WACV 2025 Oral
[Paper]

Disjoint pose and shape for 3D face reconstruction
Raja Kumar’, Jiahao Luo’, Alex Pang, James Davis
ICCV workshop 2023
[Paper]

How much does input data type impact final face model accuracy?
Jiahao Luo, Fahim Hasan Khan, Issei Mori, James Davis, etc.
CVPR 2022 Oral
[Paper]

How Accurate Is Passive Stereo For 3d Face Reconstruction?
Jiahao Luo, Eric Sandoval Ruezga, James Davis
ICIP 2022
[Paper]

Duelgan: a duel between two discriminators stabilizes the gan training
Jiaheng Wei, Minghao Liu, Jiahao Luo, Andrew Zhu, James Davis, Yang Liu
ECCV 2022
[Paper]

Low-light Image Enhancement Using Chain-consistent Adversarial Networks
Minghao Liu, Jiahao Luo, Xiaohan Zhang, Yang Liu, James Davis
ICPR 2022
[Paper]