Hanan Gani
MS Student@MBZUAI. He published 1xBMVC, 1xNeurIPS, 1xICLR paper with us.
Mohamed bin Zayed University of AI
Hanan is working to understand how to combine and optimize neural networks for label-efficient learning. His work focuses on open-world settings, multi-modal learning, Diffusion models, and 3D segmentation.
Research Outputs
- How to Train Vision Transformer on Small-scale Datasets? [BMVC, 2022]
- Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization [NeurIPS, 2023]
- LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts [ICLR, 2024]