Shaoan Xie

Hi! I’m a PhD student at Carnegie Mellon University, advised by Prof. Kun Zhang.
I have also been fortunate to intern at Adobe Research with Zhe Lin, Zhifei Zhang, and Tobias Hinz, and at Google with Yang Zhao, Zhisheng Xiao, and Kelvin C. K. Chan.

Research Highlights

My long-term research goal is to develop generative AI systems that go beyond producing realistic multi-modal data to capturing the underlying structure of the world. By embedding causal principles into machine learning and computer vision, I aim to make generative models not only powerful, but also controllable, interpretable, trustworthy, and capable of systematic generalization.

In my recent work, I have explored this vision through several directions:

• Text-to-image and video generation: advancing controllable and scalable text-driven image and video synthesis [ICML ’25, CVPR ’25, arXiv ’23, CVPR ’23, arXiv ’25].
• Conditional image generation: designing methods that flexibly adapt to conditioning signals [CVPR ’23, ICLR ’23, NeurIPS ’22, NeurIPS ’23, CVPR ’22, ICCV ’21].
• Causal representation learning: extracting disentangled and structured latent factors from visual and multimodal data to enable better generalization, enhanced controllability, and counterfactual reasoning. [ICML ’25, ICLR ’25, AISTATS ’25, ICML ’24, ICML ’22, arXiv ’24].

News

• [Aug. 2025] I will be serving as an Area Chair for ICLR 2026 — thanks for the invitation!
• [Jun. 2025] I’m attending CVPR 2025 — see you in Nashville!
• [May. 2025] Two papers accepted into ICML 2025!
• [Apr. 2025] One paper accepted as a CVPR 2025 Highlight!
• [May. 2023] My work at Adobe, SmartBrush (CVPR 2023, Highlight), is now integrated into Adobe’s flagship products — Photoshop and Firefly!
• [Jan. 2023] One paper, i-StyleGAN, accepted as an ICLR 2023 Spotlight! One of the first works to connect identifiability with multidomain image generation.

Publications

Services

Area Chair:

Session Chair:

Conference Reviewer:

Journal Reviewer: