Making pixels dance and GPUs scream for a living.
I am a Professor at the School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB). Before joining USTB in September 2026, I was an Associate Professor at the Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS) from 2022 to 2026, conducting research on image and video generation technology. Earlier, I was a faculty member at the School of Artificial Intelligence, Jilin University.
I received my Ph.D. in 2019 from the National Laboratory of Pattern Recognition (NLPR) at the Institute of Automation, CAS (CASIA), within the Multimedia Computing Group, under the supervision of Prof. Baogang Hu and Prof. Weiming Dong. During my doctoral studies, I spent one year as a visiting researcher at the University of Konstanz, Germany, collaborating with Prof. Oliver Deussen.
My current research primarily focuses on 2D digital humans, image editing, and digital art generation.
🔥News
- 🎉Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE was accepted to NeurIPS 2026 as a Spotlight. Congratulations to Yu Xu!
- 🧑⚖️Serve as Pacific Graphics (PG) 2026 TPC member.
- 🎉Joined the School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB) as a Professor.
- 🎉Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning was accepted to SIGGRAPH Asia 2026. Congratulations to Yu Xu!
- 🧑⚖️Serve as SIGGRAPH Asia 2026 TPC member.
- 🎉4 papers accepted to CVPR 2026: 2 in the main track and 2 in the Findings track.
- 🧑⚖️Serve as SIGGRAPH Asia 2025 TPC member.
🎨Representative Works
👤2D Digital Human
- IEEE TVCG 2026Make-Your-Anchor+: Temporal Consistent 2D Avatar Generation via Video Diffusion Prior
- IEEE TVCG 2026AnchorCrafter: Animate cyber-anchors selling your products via human-object interacting video generation673
- SIGGRAPH Asia 2025HOMA: Towards Generic Human-Object Interaction in Multimodal Driven Human Animation with Weak Conditions
- ACM TOG 2024Identity-preserving face swapping via dual surrogate generative models73
🖼️Image Editing
- ACM TOG 2026HeadRouter: A training-free image editing framework for MM-DiTs by adaptively routing attention heads85
- ICML 2025FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing296
- SIGGRAPH Asia 2025In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation62
- ICCV 2025Multi-turn Consistent Image Editing20
🎭Digital Arts
- CVPR 2022StyTr2: Image style transfer with transformers444
- CVPR 2023Inversion-based style transfer with diffusion models588
- ACM TOG 2023ProSpect: Prompt spectrum for attribute-aware personalization of diffusion models143
- IEEE TVCG 2025CreativeSynth: Cross-art-attention for artistic image synthesis with multimodal diffusion42
📢Join Us
I am always looking for highly motivated students or interns who are interested in 2D AIGC.
- 🎯 Research Directions: We focus on the intersection of computer vision and computer graphics, powered by modern agents.
- 💻 Required Skills: A solid foundation in mathematics (linear algebra/optimization), proficiency in Python and PyTorch for deep learning research, and a strong capability for reading and writing top-tier academic papers in English.
- ⭐ Desired Traits: We value candidates who are highly self-motivated and intellectually curious, possessing the grit and persistence required to navigate the long-term challenges of high-level academic research.
- 📧 How to Apply: Please send your CV, transcripts, and representative research works to tfan.108@gmail.com with an email subject formatted as “Your Name - University”.