Liu He
Graduate Student
Graduate Research Assistant
Joined department: Summer 2019
Education
I am final year PhD candidate at Purdue University. My advisor is Daniel Aliaga. I am interested in integrating advanced techniques to broad interdisciplinary CV/CG problems. My research focuses on advancing 3D-aware Vision-Language Model (LLaVA, etc.), generative models for image generation and editing while keeping identity, and broad topics on generation, reconstruction, and representation learning of 2D/3D layouts and scenes. I am actively looking for full-time jobs, and always open to any collaborations on interesting topics.
Selected Publications
He, L., & Aliaga, D. (2024). COHO: Context-Sensitive City-Scale Hierarchical Urban Layout Generation. In European Conference on Computer Vision (pp. 1-18). Springer, Cham.
He, L., & Aliaga, D. (2023). GlobalMapper: Arbitrary-Shaped Urban Layout Generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 454-464).
He, L., Lu, Y., Corring, J., Florencio, D., & Zhang, C. (2023, August). Diffusion-based Document Layout Generation. In International Conference on Document Analysis and Recognition (pp. 361-378). Cham: Springer Nature Switzerland.
He, L., Song, Y., Huang, H., Aliaga, D., & Zhou, X. (2024). Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation. arXiv preprint arXiv:2408.10453.
He, L., Shan, J., & Aliaga, D. (2023). Generative building feature estimation from satellite images. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-13.