activity
20212026
most citedInference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

3 citations · 3 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2026

CS-MUNet: A Channel-Spatial Dual-Stream Mamba Network for Multi-Organ Segmentation

Yuyang Zheng, Mingda Zhang, Jianglong Qin +4

Recently Mamba-based methods have shown promise in abdominal organ segmentation. However, existing approaches neglect cross-channel anatomical semantic collaboration and lack expli…

cs.CV2025

Unified Multimodal Coherent Field: Synchronous Semantic-Spatial-Vision Fusion for Brain Tumor Segmentation

Mingda Zhang, Yuyang Zheng, Ruixiang Tang +2

Brain tumor segmentation requires accurate identification of hierarchical regions including whole tumor (WT), tumor core (TC), and enhancing tumor (ET) from multi-sequence magnetic…

cs.CV2025

A Semantic Segmentation Algorithm for Pleural Effusion Based on DBIF-AUNet

Ruixiang Tang, Mingda Zhang, Jianglong Qin +3

Pleural effusion semantic segmentation can significantly enhance the accuracy and timeliness of clinical diagnosis and treatment by precisely identifying disease severity and lesio…

cs.CV2025

DCFFSNet: Deep Connectivity Feature Fusion Separation Network for Medical Image Segmentation

Mingda Zhang, Xun Ye, Ruixiang Tang +1

Medical image segmentation leverages topological connectivity theory to enhance edge precision and regional consistency. However, existing deep networks integrating connectivity of…

cs.CV2025

Knowledge-Guided Brain Tumor Segmentation via Synchronized Visual-Semantic-Topological Prior Fusion

Mingda Zhang, Kaiwen Pan

Background: Brain tumor segmentation requires precise delineation of hierarchical structures from multi-sequence MRI. However, existing deep learning methods primarily rely on visu…

cs.CV20253 cited

Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Nanye Ma, Shangyuan Tong, Haolin Jia +8

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model…