AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

NeuroRefiner: Morphology-Aware Multi-Agent Refinement for 3D Fluorescence Microscopy Neuron Segmentation

HAIYANG YAN, Jinyue Guo, Yanchao Zhang, Bingqing Wang, Zhenchen Li, Jing Liu, Jiazheng Liu, linlin li, Hua Han

ECCV 2026 · Multi-agent systems and games › LLM agents · approach: Agent data synthesis and behavior studies · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Global Inspector alone (agents vs none) (ablation)NeuroRefiner · ZBFWBF1 (%): 76.39 -> 77.29No clear effect
add Refinement Advisor to Global Inspector (ablation)NeuroRefiner · ZBFWBF1 (%): 77.29 -> 83.47Improved
add Refinement Advisor to Global Inspector (ablation)NeuroRefiner · CWMBSF1 (%): 80.34 -> 87.14Improved
add Change Validator to Inspector plus Advisor (ablation)NeuroRefiner · ZBFWBF1 (%): 83.47 -> 86.13Improved
add Change Validator to Inspector plus Advisor (ablation)NeuroRefiner · CWMBSF1 (%): 87.14 -> 88.83Improved
add patch-level projections to global MIP input (ablation)Global Inspector · ZBFWBF1 (%): 77.36 -> 80.79Improved
add patch-level projections to global MIP input (ablation)Global Inspector · CWMBSF1 (%): 81.89 -> 85.09Improved
add 0-th Betti number input (ablation)Global Inspector · ZBFWBF1 (%): 80.79 -> 86.13Improved
use cross-attention in bottleneck instead of AdaLN (ablation)TopoRefineNet · ZBFWBF1 (%): 84.38 -> 86.13Improved
use cross-attention in bottleneck instead of channel-wise dot product (ablation)TopoRefineNet · ZBFWBF1 (%): 86.07 -> 86.13No clear effect
use larger Qwen3-4B text encoder instead of 0.6B (ablation)TopoRefineNet · ZBFWBF1 (%)No clear effect
add two-stage curriculum training instead of single-stage on real defects (ablation)TopoRefineNet · ZBFWBF1 (%): 1.17% F1 degradationImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy