AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction

Xu Zhang, Ruijie Quan, Wenguan Wang, Yi Yang

ICLR 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools

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
supervise every intermediate fMRI encoder block with CLIP-layer MSE (full cascaded supervision) instead of final-block only (ablation)MindHier · NSD Subject 1CLIP score (%): 95.4% -> 97.2%Improved
use hierarchical features (final supervision only) instead of a single terminal feature (ablation)MindHier · NSD Subject 1CLIP score (%): 95.1% -> 95.4%Improved
align with later CLIP layers {18,20,22,24} instead of {12,16,20,24} (ablation)MindHier · NSD Subject 1CLIP score (%): 97.2% -> 95.4%Hurt
align with earlier CLIP layers {6,12,18,24} instead of {12,16,20,24} (ablation)MindHier · NSD Subject 1PixCorr / CLIP: PixCorr 0.273 -> 0.283; CLIP 97.2% -> 94.8%Mixed
invert guidance order (fine-to-coarse) instead of coarse-to-fine scale-aware guidance (ablation)MindHier · NSD Subject 1CLIP score (%): 97.2% -> 96.1%Hurt
use best-of-4 sampling instead of single shot (ablation)MindHier · NSDCLIP score (%): 95.0% -> 96.4%Improved
replace diffusion decoding with scale-wise autoregressionMindEye2 pipeline · NSD testinference time (s): 12.14 -> 2.64Improved
finetune on one session of fMRI dataMindHier vs MindEye2 · NSD S1CLIP score (%): 80.8% (MindEye2) -> 92.2%Improved
cross-subject 1-hour finetuning of MindHier instead of MindEye2MindHier · NSD cross-subject 1-hourCLIP score (%): 80.7% -> 80.2%Hurt
cross-subject 40-hour finetuning of MindHier instead of MindEye2MindHier · NSD cross-subject 40-hourCLIP score (%): 93.5% -> 95.8%Improved
restrict MindEye2 diffusion to 10 denoising steps to match MindHier scalesMindEye2 · NSD qualitativesemantic fidelityHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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