Guandong Li
Deep Learning Algorithm Engineer
I lead core algorithm research on Typemovie, AI Photo Frame, and Super Drawing — large-model-native applications for intelligent marketing. Previously at Suning, I worked on AIGC and computer vision for e-commerce, covering e-commerce LLMs, multimodal LLMs, video editing, lip-sync-driven 2D digital humans, and diffusion-based image synthesis, along with OCR and tamper detection systems.
My academic background is in deep learning for remote sensing — M.S. from Hefei University of Technology, with one paper selected for the ESI top 1%. Current research spans AIGC, LLMs, LVMs, diffusion models, video editing, and digital humans.
News
- 2026 Paper EditIDv2: Editable ID Customization with Data-Lubricated ID Feature Integration for Text-to-Image Generation accepted to Multimedia Systems.
- 2026 Paper Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating accepted to International Journal of Image and Data Fusion.
- 2026 Paper DGCNet: An Efficient 3D-DenseNet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification accepted to Spectroscopy Letters.
- 2025 Paper EditID: Training-Free Editable ID Customization for Text-to-Image Generation accepted to Findings of EMNLP 2025.
- 2025 Paper Dynamic 3D KAN Convolution with Adaptive Grid Optimization for Hyperspectral Image Classification accepted to Arabian Journal for Science and Engineering.
Experience
- Key member of the iFlytek Typemovie project, a native application powered by large-scale AI models, enabling innovative solutions for intelligent marketing.
- Responsible for core algorithm research on Typemovie, AI Photo Frame, and Super Drawing.
- Core member of the algorithm team, focusing on AIGC and computer vision applications for e-commerce.
- Developed solutions for e-commerce LLMs, multimodal LLMs, video editing, lip-sync-driven 2D digital humans, and image synthesis using diffusion models.
- Contributed to OCR and tamper detection systems.
Research focused on deep learning for remote sensing image processing. Secretary of the 3rd Party Branch of the College. Outstanding graduate with thesis nominated for excellent graduation thesis. ESI top 1% paper.