About
Jiaxi Gu is an AI researcher at Tencent, where he develops AIGC models for advertising creative systems. He previously served as a senior engineer at Huawei Noah's Ark Lab. He earned his Ph.D. in Computer Science and Technology from Northwestern Polytechnical University under the supervision of Yunhao Liu.
His research centers on generative models, vision-language models, and multimodal learning, with a particular focus on video diffusion, controllable generation, and multimodal pre-training.
Selected works
- Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping, ICML 2026
- MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance, ICML 2025
- BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models, CVPR 2024
- Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark, NeurIPS 2022