AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Cross-Timestep: 3D Diffusion Model with Trans-temporal Memory LSTM and Adaptive Priori Decoding Strategy for Medical Segmentation

Shangqian Wu, Siyuan Shen, Yahan Li, Zhijian Huang, Ziyu Fan, Yuanpeng Zhang, YI WANG, Lei Deng

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools

Read the paperCheck your idea against 137,217 papers

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 SC-tLSTM to APDS baseline (ablation)Cross-Timestep · LNCTVSegDice: 77.3 -> 82.1Improved
add FFT-tLSTM to APDS baseline (ablation)Cross-Timestep · LNCTVSegDice: 77.3 -> 81.8Improved
add both SC-tLSTM and FFT-tLSTM (ablation)Cross-Timestep · LNCTVSegDice: 82.1 -> 83.7Improved
add SC-tLSTM to APDS baseline (ablation)Cross-Timestep · OASegDice: 67.5 -> 71.3Improved
add the t-cell on top of LSTM variants (ablation)tLSTM · LNCTVSegDice: 82.5 -> 83.7Improved
add temporal memory (standard LSTM replaced by Conv-LSTM variant) (ablation)tLSTM · LNCTVSegDice: 79.5 -> 81.1Improved
add Linear-GRU variant versus LSTM only (ablation)tLSTM · LNCTVSegDice: 79.5 -> 79.2No clear effect
use 1000 diffusion steps instead of 300 (ablation)Cross-Timestep · LNCTVSegDice: 79.3 -> 83.7Improved
use 1000 diffusion steps instead of 500 (ablation)Cross-Timestep · LNCTVSegDice: 82.8 -> 83.7Improved
use Cross-Timestep instead of Diff-UNetDiff-UNet · OASegDice: 71.5 -> 72.8Improved
use Cross-Timestep instead of Diff-UNet (training time)Diff-UNet · LNCTVSegtraining time (h): 29.2 -> 33.4Hurt

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