Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN

Mix-LN：通过结合Pre-LN与Post-LN释放深层网络的能力.

北京地铁三号线路考

Beijing Metro Line 3 Inspection.

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

DINO-X：开放世界目标检测与理解的统一视觉模型.

DODA: Diffusion for Object-detection Domain Adaptation in Agriculture

DODA：农业中目标检测领域自适应的扩散模型.

CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale

CLIBD：融合视觉与基因组学的大规模生物多样性监测.

Adapting the Segment Anything Model for Plant Recognition and Automated Phenotypic Parameter Measurement

微调SAM模型实现植物识别和表型参数自动测量.