Songhua Liu

About Me

I am an incoming assistant professor, Ph.D. advisor, at the School of Artificial Intelligence, Shanghai Jiao Tong University. I am about to obtain my Ph.D. at the Department of Electronic and Computer Engineering, National University of Singapore this June, supervised by Prof. Xinchao Wang. Before that, I received my bachelor’s degree in the Department of Computer Science and Technology from Nanjing University in 2021. I was also fortunate to work as a research intern at Rutgers University under the supervision of Prof. Hao Wang and at Baidu Inc. under the supervision of Tianwei Lin.

My research interests include visual synthesis and training with synthetic data. Since 2020, I have published over 10 first-author research papers at top journals/conferences on these topics. Multiple works are selected as paper award nomination, oral, highlight, and spotlight. During my doctoral studies, I received NUS Research Scholorship and the 2023 National Award for Outstanding Self-financed Chinese Students Abroad.

Currently, I am creating Learning and Synthesis Hub and recruiting Ph.D. students (2~3 every year starting from fall 2026), Master students (1~2 every year starting from fall 2026), and multiple research interns. If you are interested in working with me at Shanghai Jiao Tong University on the following topics:

1. Model Editing for Novel Functionalities, Efficiency, Generalizability, and Safety;
2. Training with Synthetic Data;
3. Visual Generative Model;
4. Applications of the above topics to broader domains, e.g., art, science, robotics, multimedia, etc.,

feel free to reach out via songhua.liu@u.nus.edu / liusonghua_site@163.com. We are always looking for self-motivated students actively.

News

Last Update: 2025.06

[2025.05] 🔥We release IEAP: Your Free GPT-4o Image Editor. It decouples a complex image editing instruction into several programmable atomic operations and achieves compelling performance! Codes are available here!🚀 Demo is available here.🤗

[2025.05] 🔥We release LLaVA-Meteor, a novel, efficient, and promising method to process visual tokens in VLM.

[2025.05] 🔥2 papers are accepted by ICML 2025! Congratulations to all co-authors!🎉

[2025.04] 🔥We release Flash Sculptor, an efficient and scalable solution to reconstruct a complex and compositional 3D scene from merely a single image! Try it here🚀

[2025.03] 🔥We release URAE: Your Free FLUX Pro Ultra. It adapts pre-trained diffusion transformers like FLUX to 4K resolution with merely 3K training samples! Codes are available here!🚀 Demos are available here and here.🤗

[2025.03] 🔥We release OminiControl2! OminiControl1 has achieved impressive results on controllable generation. Now, OminiControl2 makes it efficient as well!

[2025.03] 🔥We release CFM! Spectral Filtering provides dataset distillation with a unified perspective!

[2025.02] 🔥3 papers are accepted by CVPR 2025! Congratulations to all co-authors!🎉

[2025.02] 🔥We release a benchmark for large-scale dataset compression here. Try it here!🚀

[2024.12] 🔥We release CLEAR, a simple-yet-effective strategy to linearize the complexity of pre-trained diffusion transformers, such as FLUX and SD3. Try it here!🚀

[2024.12] 🔥We release OminiControl, a minimal yet powerful universal control framework for Diffusion Transformer models like FLUX. Try it here!🚀

Selected Publications and Preprints