Computer Vision; PhD student@ZJU
Osprey. [CVPR2024] The code for "Osprey: Pixel Understanding with Visual Instruction Tuning"
TokenPacker. The code for "TokenPacker: Efficient Visual Projector for Multimodal LLM", IJCV2025
APro. The code for "Label-efficient Segmentation via Affinity Propagation". [NeurIPS2023]
