AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

TIM: Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology Report Generation

Yiheng Dong, Yi Lin, Shilong Huang, Xiyan Yang, Xin Yang

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 0 citations (OpenAlex)

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 dynamic progression modeling branch with perception frames and a video encoder (ablation)Base single-timepoint LRRG model · Longitudinal-MIMIC testF1: 0.404 -> 0.427Improved
add dual-timepoint report generation (ablation)Model with DPM · Longitudinal-MIMIC testF1: 0.427 -> 0.446Improved
add static pathology contrastive loss Lspr (ablation)Model with DPM and DRG · Longitudinal-MIMIC testF1: 0.446 -> 0.460Improved
add progression alignment loss Ldpm (ablation)Model with DPM and DRG · Longitudinal-MIMIC testF1: 0.446 -> 0.451Improved
add both Lspr and Ldpm (full Stage I) (ablation)Model with DPM and DRG · Longitudinal-MIMIC testF1: 0.446 -> 0.483Improved
add prior difference information (error triplets) as Stage II input (ablation)TIM Stage II · Longitudinal-MIMIC testF1: 0.453 -> 0.487Improved
add similarity-based mutual-refinement loss L∆ (ablation)TIM Stage II · Longitudinal-MIMIC testF1: 0.487 -> 0.511Improved
apply Stage II mutual refinement on top of Stage ITIM · Longitudinal-MIMIC testF1: 0.483 -> 0.511Improved
use 2 perception frames rather than none (ablation)TIM Stage I · Longitudinal-MIMIC testF1: 0.454 -> 0.483Improved
increase perception frames from 2 to 10 (ablation)TIM Stage I · Longitudinal-MIMIC testF1: 0.483 -> 0.443Hurt
increase refinement iterations from 3 to 5 (ablation)TIM Stage II · Longitudinal-MIMIC testF1: 0.511 -> 0.510No clear effect
use larger LLM backbone (Vicuna-13B vs LLaMA2-7B) (ablation)TIM · Longitudinal-MIMIC testF1 (Stage II): 0.511 -> 0.529Improved

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