AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies

Yuxiang Feng, Juncheng Wang, Chao Xu, Wenlong Hou, Huihan Wang, Yijie Qian, Yang Liu, Baigui Sun, Yong Liu, Shujun Wang

ECCV 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 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
predict latent drift instead of pixel-level future (ablation)Latent Drift · ADNI+AIBL forecastingFID (i3d): 44.38 -> 13.92Improved
predict latent drift instead of pixel-level future (ablation)Latent Drift · ADNI+AIBL forecastingDiff-SSIM: 0.7625 -> 0.8205Improved
predict latent drift instead of pixel-level future (ablation)Latent Drift · ADNI+AIBL forecastingAccuracy: 77.19 -> 88.33Improved
use FSQ instead of vector quantization (ablation)Latent Drift · ADNI+AIBL forecastingAccuracy: 86.67 -> 88.24Improved
use FSQ instead of residual VQ (ablation)Latent Drift · ADNI+AIBL forecastingAccuracy: 84.56 -> 88.24Improved
use FSQ instead of lookup-free quantization (ablation)Latent Drift · ADNI+AIBL forecastingF1: 84.02 -> 87.41Improved
use FSQ instead of BSQ (ablation)Latent Drift · ADNI+AIBL forecastingF1: 82.75 -> 87.41Improved
use FSQ instead of VQ or LFQ for structural similarity (ablation)Latent Drift · ADNI+AIBL forecastingDiff-SSIM: 0.8249 -> 0.8224Hurt
use FSQ grid [8,8,8,5,5,5] instead of [8,8,8,6,5] (ablation)Latent Drift · ADNI+AIBL forecastingrFID: 27.07 -> 12.78Improved
use FSQ grid [8,8,8,5,5,5] instead of coarse [8,6,5] (ablation)Latent Drift · ADNI+AIBL forecastingAccuracy: 86.84 -> 88.24Improved
use autoregressive generator instead of context-conditioning (ablation)Latent Drift · ADNI+AIBL forecastingAccuracy: 83.77 -> 88.33Improved
use autoregressive generator instead of masked-conditioning (ablation)Latent Drift · ADNI+AIBL forecastingrFID: 23.17 -> 13.92Improved

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