Shilin Xu

RMP-SAM. [ICLR 2025 oral] RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything

FashionFormer. Code for our ECCV-2022 work: Fashionformer A simple, effective and unified baseline for human fashion segmentation and recognition

dst-det. [TCSVT] state-of-the-art open vocabulary detector on COCO/LVIS/V3Det

Mixed-R1.

LLaVADI. Python

VLMEvalKit. Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks