Research map / Image generation / Autoregressive and latent generation
Short-to-Long Functional Connectivity Transfer via Structure-Aware Latent Diffusion
Ishmael Benjamin Torres Aguilar, Yufeng Liu, Zhengwu Zhang
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 SC and covariate conditioning (ablation) | SALD · ABCD tau=1-3 | Frobenius / MSE: tau=1 Frob 14.65 -> 14.27; MSE 285.06 -> 267.25 | Improved |
| add structural connectivity conditioning (ablation) | SALD · ABCD tau=1 | Frobenius / MSE: tau=1 Frob 14.77 -> 14.27; MSE 285.15 -> 267.25 | Improved |
| add short-scan FC input (ablation) | SALD · ABCD tau=1-3 | Frobenius / MSE: tau=1 MSE 272.92 -> 267.25; tau=3 MSE 272.92 -> 250.73 | Improved |
| add one-step denoising anchoring (ablation) | SALD · ABCD tau=1-3 | Frobenius / MSE: tau=1 Frob 13.32 (without) vs 14.27; tau=3 Frob 12.21 vs 11.77 | Mixed |
| replace direct phenotype supervision with distillation from long-scan predictor (ablation) | SALD · ABCD tau=1-3 | Frobenius / MSE: tau=2 Frob 15.43 -> 12.25; tau=3 MSE 256.04 -> 250.73 | Improved |
| reward-guided LoRA steering on top of conditional diffusion | Conditional DDPM · ABCD tau=2-10 | differential identifiability: tau=2 8.49 -> 10.57; tau=10 18.17 -> 20.83 | Improved |
| reward-guided LoRA steering on top of conditional diffusion | Conditional DDPM · ABCD tau=1 | differential identifiability: 4.21 -> 4.10 | No clear effect |
| reward-guided steering vs likelihood-only diffusion | Conditional DDPM · ABCD tau=1 | phenotype prediction MSE: 288.52 -> 267.25 | Improved |
| reward steering on extra phenotypes (UPPS, CBCL, SDS) | SALD · ABCD additional phenotypes | predictive variance / correlation | Mixed |
| steering reward for generative fidelity | SALD · ABCD | Frobenius distance: tau=1 15.13 -> 14.27 | Improved |
Closest papers by meaning
- Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition (ICLR 2025 · similarity 0.89)
- $\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes (NeurIPS 2024 · similarity 0.86)
- Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens (NeurIPS 2025 · similarity 0.86)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.86)
- FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model (NeurIPS 2026 · similarity 0.86)
- Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints (NeurIPS 2025 · similarity 0.85)
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.
