Research
My research focuses on generative models, particularly controllable and interactive video generation.
I am interested in developing user-friendly and physically grounded generative systems that allow intuitive control and seamless interaction.
I am also passionate about understanding the efficiency, structure, and emergent locality of generative modeling to make models more interpretable and scalable.
|
|
Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation
Beijia Lu,
Ziyi Chen,
Jing Xiao,
Jun-Yan Zhu
SIGGRAPH Asia, 2025
paper /
project page /
code
|
|
AniFeats: Animate 3D Feature Meshes for Character Video Generation
Beijia Lu,
Zekai Gu,
Zhiyang Dou,
Haotian Yuan,
Chenyang Si,
Yukang Cao,
Yuming Jiang,
Yuan Liu,
Wenping Wang,
Ziwei Liu
Submitted to IEEE Transactions on Visualization and Computer Graphics (TVCG)
paper /
project page
|
|
ColonNeRF: Hierarchical Neural Radiance Fields for High-Fidelity Long-Sequence Colon Reconstruction
Yufei Shi*,
Beijia Lu*,
Jia-Wei Liu,
Ming Li,
Mike Zheng Shou
Neurocomputing
paper /
project page
|
|
Adding 3D Geometry Control to Diffusion Models
Wufei Ma*,
Qihao Liu*,
Jiahao Wang*,
Xiaoding Yuan,
Angtian Wang,
Yi Zhang,
Zihao Xiao,
Guofeng Zhang,
Beijia Lu,
Ruxiao Duan,
Yongrui Qi,
Adam Kortylewski,
Yaoyao Liu,
Alan Yuille
ICLR, 2024 (Spotlight)
paper /
project page /
code
|
|
SemTrack: A Large-scale Dataset for Semantic Tracking in the Wild
Pengfei Wang*,
Xiaofei Hui*, Jing Wu*, Zile Yang*, Kian Eng Ong*, Xinge Zhao, Beijia Lu, Dezhao Huang, Evan Ling, Weiling Chen, Keng Teck Ma, Minhoe Hur,
Jun Liu
ECCV, 2024
paper /
project page /
code
|
Miscellaneous
• Sunny is always a clingy little baby, btw can you find Sunny's eyes in the image?
• Huahua and Fugui often fight, but they are also a pair of siblings who can't be without each other.
• They give me the inspiration to strive, and I will love them forever. ❤
|
|