Jiajun Liang

Jiajun Liang

Perceive Generate Act

From visual perception to embodied intelligence.

Photo of Jiajun Liang (梁嘉骏)

ActEmbodied AI

Now I am building embodied AI systems powered by frontier models to perceive, reason, and act in the physical world.

GenerateGenerative AI

I built and deployed RLHF systems for multimodal video generation at leading companies from 2024 to 2026, including Kling, covering preference data pipelines, reward modeling, and scalable, stable reinforcement learning.

PerceivePerception & Recognition

From 2016 to 2024, I led algorithm teams at Megvii and Jiiov, developing human-centric 2D and 3D perception and biometric recognition systems for faces, hands, and fingers, deployed on over one billion mobile devices.

Publications at top-tier AI and computer vision conferences. Google Scholar ↗

I am looking for self-motivated interns for Embodied AI.

News

About me

I am Jiajun Liang, a researcher based in Beijing, originally from Zhongshan, Guangdong.
I received my Master of Science in Computer Science from Tsinghua University in 2017 and my Bachelor of Engineering in Electrical Engineering from Huazhong University of Science and Technology in 2014.
My research spans multimodal perception, generation, and embodied intelligence.

Working Experience

Selected Publications

See full list at Google Scholar
Video Generation & RLHF
Flow-GRPO: Training Flow Matching Models via Online RL
J. Liu, G. Liu, Jiajun Liang, Y. Li, J. Liu, X. Wang, P. Wan, D. Zhang, W. Ouyang
NeurIPS, 2025 [Paper] [Code]
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
J. Wang, Jiajun Liang, J. Liu, H. Liu, G. Liu, J. Zheng, W. Pang, A. Ma, Z. Xie, X. Wang
CVPR, 2026 [Paper] [Code]
Improving Video Generation with Human Feedback
J. Liu, G. Liu, Jiajun Liang, Z. Yuan, X. Liu, M. Zheng, X. Wu, Q. Wang, M. Xia, X. Wang
NeurIPS, 2025 [Paper] [Code]
GARDO: Reinforcing Diffusion Models without Reward Hacking
He, H., Ye, Y., Liu, J., Jiajun Liang, Wang, Z., Yuan, Z., Wang, X., Mao, H., Wan, P. and Pan, L.
NeurIPS, 2026 [Paper] [Code]
Scaling Image and Video Generation via Test-Time Evolutionary Search
H. He, Jiajun Liang, X. Wang, P. Wan, D. Zhang, K. Gai, L. Pan
NeurIPS Workshop, 2025 [Paper] [Code]
VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
Q. Wang, J. Liu, Jiajun Liang, Y. Jiang, Y. Zhang, J. Chen, Y. Zheng, X. Wang, P. Wan, X. Yue
ICML, 2026 [Paper] [Code]
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
J. Wang, X. Zhou, Jiajun Liang, K. Liu, W. Pang, Z. Xie, T. Pang, X. Liang
Preprint, 2026 [Paper] [Code] [Project]
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
Y. Wang, O. Li, Y. Xu, B. Liao, Jiajun Liang, J. Li, M. Wang, X. Wang, P. Wan, K. Liu, X. Wang
NeurIPS, 2026 [Paper] [Code] [Project]
Diffusion Models
LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding
S. Zhang, S. Liang, Y. Tan, Z. Chen, L. Li, G. Wu, Y. Chen, S. Li, Z. Zhao, C. Chen, Jiajun Liang, Y. Tang
NeurIPS, 2025 [Paper] [Code]
MegActor-Sigma: Unlocking Flexible Mixed-Modal Control in Portrait Animation with Diffusion Transformer
S. Yang, H. Li, J. Wu, M. Jing, L. Li, R. Ji, Jiajun Liang, H. Fan, J. Wang
AAAI, 2025 [Paper] [Code]
MegActor: Harness the Power of Raw Video for Vivid Portrait Animation
S. Yang, H. Li, J. Wu, M. Jing, L. Li, R. Ji, Jiajun Liang, H. Fan
Preprint, 2024 [Paper] [Code]
HiDiffusion: Unlocking Higher-Resolution Creativity and Efficiency in Pretrained Diffusion Models
S. Zhang, Z. Chen, Z. Zhao, Y. Tang, Y. Chen, W. Cao, Jiajun Liang
ECCV, 2024 [Paper] [Project]
The Velocity Deficit: Initial Energy Injection for Flow Matching
L. Li, Z.-W. Hong, S. Zhang, B. Lin, J. Li, Y. Tang, Jiajun Liang
ICML, 2026 [Paper] [Project]
Knowledge Distillation & Efficient AI
Efficient One-Pass Self-Distillation with Zipf’s Label Smoothing
Jiajun Liang, L. Li, Z. Bing, B. Zhao, Y. Tang, B. Lin, H. Fan
ECCV, 2022 [Paper] [Code]
Decoupled Knowledge Distillation
B. Zhao, Q. Cui, R. Song, Y. Qiu, Jiajun Liang
CVPR, 2022 [Paper] [Code]
Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers
S. Wei, T. Ye, S. Zhang, Y. Tang, Jiajun Liang
CVPR, 2023 [Paper] [Code]
Cumulative Spatial Knowledge Distillation for Vision Transformers
B. Zhao, R. Song, Jiajun Liang
ICCV, 2023 [Paper] [Code]
DOT: A Distillation-Oriented Trainer
B. Zhao, Q. Cui, R. Song, Jiajun Liang
ICCV, 2023 [Paper] [Code]
Asymmetric Decision-Making in Online Knowledge Distillation
Z. Chen, B. Zhao, Y. Ge, Y. Chen, R. Song, Jiajun Liang
ICML, 2025 [Paper]
Vision & Recognition
EAST: An Efficient and Accurate Scene Text Detector
X. Zhou, C. Yao, H. Wen, Y. Wang, S. Zhou, W. He, Jiajun Liang
CVPR, 2017 [Paper] [Code]
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
S. Dong, J. Wang, R. Ji, Jiajun Liang, H. Fan, Z. Ge
CVPR, 2023 [Paper] [Code]
A Simple Baseline for Efficient Hand Mesh Reconstruction
Z. Zhishan, Z. Shihao, L. Zhi, Z. Minqiang, T. Yao, Jiajun Liang
CVPR, 2024 [Paper] [Code]
© Jiajun Liang
× Full size poster