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

arXiv: https://arxiv.org/abs/2607.08270 · HTML: https://mlsanity.com/paper/2607.08270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 65 references that are in the map.
- First posted on arXiv 9 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Lipschitz regularity of deep neural networks: analysis and efficient estimation](https://mlsanity.com/paper/1805.10965/) (2018)
- [Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://mlsanity.com/paper/2304.01186/) (2023)
- [Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks](https://mlsanity.com/paper/1906.04893/) (2019)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network](https://mlsanity.com/paper/1904.12200/) (2019)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning](https://mlsanity.com/paper/2506.05207/) (2025)
- [Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1908.02498/) (2019)
- [Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models](https://mlsanity.com/paper/2111.14923/) (2021)
- [Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledge](https://mlsanity.com/paper/2405.03328/) (2024)
- [LoL: Longer than Longer, Scaling Video Generation to Hour](https://mlsanity.com/paper/2601.16914/) (2026)
- [Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model](https://mlsanity.com/paper/2212.08034/) (2022)
- [Taming Data and Transformers for Audio Generation](https://mlsanity.com/paper/2406.19388/) (2024)
- [Brain Latent Progression: Individual-based Spatiotemporal Disease Progression on 3D Brain MRIs via Latent Diffusion](https://mlsanity.com/paper/2502.08560/) (2025)
- [Synchronized Video-to-Audio Generation via Mel Quantization-Continuum Decomposition](https://mlsanity.com/paper/2503.06984/) (2025)
- [Synthesizing Individualized Aging Brains in Health and Disease with Generative Models and Parallel Transport](https://mlsanity.com/paper/2502.21049/) (2025)
- [Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformers](https://mlsanity.com/paper/2510.04577/) (2025)
- [PhyEduVideo: A Benchmark for Evaluating Text-to-Video Models for Physics Education](https://mlsanity.com/paper/2601.00943/) (2026)
- [Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation](https://mlsanity.com/paper/2512.24100/) (2025)
- [Neural Autoregressive Modeling of Brain Aging](https://mlsanity.com/paper/2507.22954/) (2025)
- [Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding](https://mlsanity.com/paper/2601.14304/) (2026)

## Abstract (arXiv)

Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challenging because true progression signals are subtle in longitudinal MRI. In this low-signal regime, transferring modern generative sequence models directly is unreliable: training is dominated by stable baseline anatomy and confounded by dense, sample-specific nuisance variation. We first provide a theoretical analysis that explains these failures through two modes. Identity collapse occurs when optimization is driven toward reproducing the current anatomy, which prevents the model from learning faint temporal change. The continuous interpolation trap arises when standard smooth networks cannot separate localized biological drift from pervasive noise, which leads to spurious changes that diffuse across the volume. To address both issues, we propose Latent Drift, a progressive generative framework that learns change in a compressed semantic representation rather than synthesizing full-resolution anatomy. This design removes pixel-level identity from the prediction target and concentrates model capacity on progression-relevant dynamics. We further apply Finite Scalar Quantization to the learned change representation, which suppresses small, high-frequency nuisance fluctuations while preserving consistent structural drift. Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines across generative fidelity and clinically relevant evaluation metrics. Project page: hrefhttps://cutepkq.github.io/latent-drifthttps://cutepkq.github.io/latent-drift.