AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

Stochastic Optimal Control for Continuous-Time fMRI Representation Learning

Joonhyeong Park, Byoungwoo Park, Chang-Bae Bang, Jungwon Choi, Hyungjin Chung, Byung-Hoon Kim, Juho Lee

ICLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Self-supervised neuroimaging representations · 3 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
increase pretraining sequence length (number of timesteps) from 80 to 240 (ablation)BDO (86M) · HCP-A (linear probing)age MSE: 0.587 -> 0.348Improved
increase timesteps from 160 to 240 (ablation)BDO (86M) · HCP-A gender (linear probing)accuracy (%): 72.00 -> 72.22No clear effect
add JEPA regularizer (tau > 0) to MAE-only objective (ablation)BDO · HCP-A age regressionPearson rhoImproved
raise mask ratio beyond 75% (ablation)BDO · HCP-A age regressionPearson rhoHurt
scale model size (5M, 21M, 86M) and pretraining data (ablation)BDO · HCP-A age and diagnosisperformanceImproved
fine-tune BDO instead of linear probe (ablation)BDO (86M) · UKB ageMSE: 0.600 -> 0.481Improved

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