Ph.D. student in Institute of Information Engineering, Chinese Academy of Sciences, interest in Vision-Language Alignment.
osrcir. Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval [CVPR 2025 Highlight]
72context-i2w. Context-I2W: Mapping Images to Context-dependent words for Accurate Zero-Shot Composed Image Retrieval [AAAI 2024 Oral]
54vlpmarker. Jupyter Notebook
19predicir. CVPR 2025
13AlignCMSS.
8denoise-i2w-tmm.
4