Scholar
Jinheng Xie
Google Scholar ID: smbRMokAAAAJ
National University of Singapore
Citations & Impact
Citations
1,541
H-index
13
i10-index
16
Publications
20
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- - 2025: Show-o2: Improved Native Unified Multimodal Models (NeurIPS)
- - 2025: Show-o: One Single Transformer to Unify Multimodal Understanding and Generation (ICLR, PREMIA Best Student Paper Award 2025)
- - 2025: CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation (IJCV)
- - 2025: Faster Diffusion via Temporal Attention Decomposition (TMLR)
- - 2024: Cross-Attention Makes Inference Cumbersome in Text-to-Image Diffusion Models (arXiv)
- - Awards:
- - 2025: PREMIA Best Student Paper Award 2025
- - Projects:
- - Development and release of Show-o and Show-o2 models
Research Experience
- - Work Experience:
- - Show Lab, National University of Singapore, PhD Student (2023 to present)
- - Research Projects:
- - Development and training of Show-o and Show-o2 models
- - Research on unified models for multimodal understanding and generation
- - Position: PhD Student
Education
- - Degree: PhD
- - University: National University of Singapore
- - Advisor: Prof. Mike Shou
- - Duration: 2023 to present
- - Major: Computer Science
Background
- - Research Interests: Label-efficient learning, weakly-supervised object localization, semantic segmentation, visual prompt learning, controllable image synthesis, multimodal understanding and generation
- - Professional Field: Computer Vision, Machine Learning
- - Brief Introduction: Third-year PhD student at Show Lab, National University of Singapore, working with Prof. Mike Shou. Focused on the development of unified models for multimodal understanding and generation.
Miscellany
- - Personal Interests: Music
