Xiaoyu Liu

Efficient Quantization-Aware Adaptation for Visual Foundation Models

SHERPA: Fine-tuning Segment Anything Models with Task-relevant Guidance

CBQ: Cross-Block Quantization for Large Language Models

Multi-Granularity Semantic Revision for Large Language Model Distillation

MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation

MaskTwins: Dual-form Complementary Masking for Domain-Adaptive Image Segmentation

TokenUnify: Scalable Autoregressive Pretraining for Large Scale EM Image Segmentation