Scholar
Ji Xie
Google Scholar ID: Wv7ItTYAAAAJ
Research Intern, UC Berkeley
Citations & Impact
Citations
47
H-index
3
i10-index
2
Publications
4
Co-authors
5
list available
Publications
Resume (English only)
Academic Achievements
- 1. Paper: 'Reconstruction Alignment Improves Unified Multimodal Models', Preprint (2025).
- 2. Paper: 'In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large-Scale Diffusion Transformer', NeurIPS 2025.
- 3. Paper: '3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation', ICLR 2025 (Spotlight).
- 4. Invited Talk: 'Reconstruction Alignment Improves Unified Multimodal Model' at Apple Research, October 2025.
- 5. SenseTime Scholarship, Top 30 recipients annually in China, June 2025.
- 6. Gold Medal, International Collegiate Programming Contest (ICPC) regional, October 2022.
- 7. Gold Medal, China Collegiate Programming Contest (CCPC) regional, October 2022.
Research Experience
- Research Intern at BAIR (UC Berkeley), advised by Dr. Xudong Wang and Prof. Trevor Darrell.
Education
- Bachelor of Engineering in Computer Science and Technology with Honors from Zhejiang University, Chu Kochen Honors College, expected to graduate in June 2026. GPA: 93.6/100, rank: 2/147.
Background
- Research interests include Computer Vision, Generative Models, and Multimodal. Currently exploring Unified Multimodal Models, Video Generation, and World Model.
Miscellany
- Was a member of the ZJU ACM/ICPC team and achieved a rating of 2478 on Codeforces. Old blog contains competitive-programming notes.
