Research map / Image generation / Autoregressive and latent generation
Conditional Recurrent Flow: Conditional Generation of Longitudinal Samples With Applications to Neuroimaging
Seong Jae Hwang, Zirui Tao, Won Hwa Kim, Vikas Singh
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE Diagnosis, Control vs Progression | significant ROIs: 11 -> 12 | Improved |
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE ADAS13, Control vs Progression | significant ROIs: 12 -> 14 | Improved |
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE CDR-SB, Control vs Progression | significant ROIs: 7 -> 9 | Improved |
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE MMSE and RAVLT-I, Control vs Progression | significant ROIs: 2 -> 2 | No clear effect |
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE Diagnosis, Control vs Early-progression | significant ROIs: 2 -> 4 | Improved |
| add temporal context gating (TCG) to CRow (ablation) | CRow · TADPOLE ADAS13, Control vs Early-progression | significant ROIs: 4 -> 5 | Improved |
| replace cINN with recurrent flow CRow | conditional invertible network · TADPOLE Diagnosis, Control vs Progression | significant ROIs: 4 -> 11 | Improved |
| replace cINN with recurrent flow CRow | conditional invertible network · TADPOLE CDR-SB, Control vs Progression | significant ROIs: 0 -> 7 | Improved |
| replace cINN with recurrent flow CRow | conditional invertible network · TADPOLE Diagnosis, Control vs Early-progression | significant ROIs: 0 -> 2 | Improved |
| generate synthetic samples instead of using raw training data | group statistical analysis · TADPOLE Control vs Progression | significant ROIs: no significant ROIs with raw data | Improved |
| increase generated samples from 100 to 150 per group | Control vs Early-progression analysis · TADPOLE Early-progression | significant ROIs: no significant ROIs at N=100 -> several at N=150 | Improved |
Closest papers by meaning
- Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies (ICLR 2025 · similarity 0.90)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.86)
- Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series (NeurIPS 2024 · similarity 0.86)
- Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation (NeurIPS 2025 · similarity 0.86)
- Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand (NeurIPS 2024 · similarity 0.85)
- Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints (AAAI 2025 · similarity 0.84)
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.
