Scholar
Xingyu Fu
Google Scholar ID: 5p_uBNQAAAAJ
Princeton University
Citations & Impact
Citations
648
H-index
11
i10-index
11
Publications
17
Co-authors
9
list available
Contact
Publications
Resume (English only)
Academic Achievements
- ICML 2025: Presented 'ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding'.
- COLM 2024: Presented 'Commonsense-T2I: Can Text-to-Image Generation Models Understand Commonsense?'.
- ECCV 2024 (Spotlight): Published 'BLINK: Multimodal Large Language Models Can See but Not Perceive' with 36K+ downloads.
- NeurIPS 2024: Co-authored 'Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models'.
- ICLR 2025: Co-developed MUIRBENCH, a comprehensive benchmark for robust multi-image understanding.
- CVPR 2025: Contributed to 'Science-T2I: Addressing Scientific Illusions in Image Synthesis'.
- ICLR 2024: Contributed to ImagenHub for standardized evaluation of conditional image generation models.
- NAACL 2024: Co-authored work on deceptive semantic shortcuts and hallucination in reasoning chains.
