Sicheng Yang

segdino. SegDINO: An Efficient Design for Medical and Natural Image Segmentation with DINO-V3

segdino_v2. [MICCAI 2026, Early Accepted] SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation

XJTU-CSTE-Mentor-Group. 西交计学组资料仓库(XJTU-CS Experimental Class Resource Repository)

VQ-Seg. [NeurIPS 2025] VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

VAEVQ. [AAAI 2026, Oral] VAEVQ: Enhancing Discrete Visual Tokenization through Variational Modeling

LCM-Net. [IEEE TMI 2026] LCM-Net: LLM-driven Cross-Modality MoE Feature Fusion Network for Cancer Survival Analysis

RSF. [MICCAI 2026] Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis

BraTS-MTrans. Medical image reconstruction based on the BraTS dataset.

EasyGPTQ. A simple self-implemented example demonstrating both GPTQ and Quarot, a custom quantization method designed for efficient inference of LLMs.