AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

MoLF: Mixture-of-Latent-Flow for Pan-Cancer Spatial Gene Expression Prediction from Histology

Susu Hu, Stefanie Speidel

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 0 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
replace dense attention velocity network with Mixture-of-Experts (ablation)MoLF · HEST-1k Top50 HVG averagePCC: 0.209 -> 0.383Improved
replace dense attention velocity network with Mixture-of-Experts (ablation)MoLF · HEST-1k Hallmark genes overallPCC: 0.127 -> 0.185Improved
use MoE instead of dense transformer in synthetic task (ablation)MoLF flow · Conditional eight Gaussians2-Wasserstein distance: 0.315 -> 0.292Improved
add sinusoidal positional encoding on image features (ablation)MoLF · HEST-1k Top50 HVG averagePCC: 0.386 -> 0.383No clear effect
add sinusoidal positional encoding on image features (ablation)MoLF · HEST-1k Hallmark genes overallPCC: 0.173 -> 0.185Improved
train on pan-cancer data instead of skin cancer only (ablation)MoLF · Zero-shot mouse melanomaPCC: 0.127 -> 0.202Improved
MoLF flow matching with MoE versus foundation model STPathMoLF · HEST-1k Top50 HVG averagePCC: 0.361 -> 0.382Improved
MoLF versus STFlow single-flow baselineflow matching for ST · HEST-1k Hallmark genes overallPCC: 0.122 -> 0.185Improved
use the large foundation model STPath instead of an MLPHallmark gene prediction · HEST-1k Hallmark genes overallPCC: 0.171 -> 0.143Hurt
use diffusion (STEM) instead of an MLPHVG prediction · HEST-1k Top50 HVG averagePCC: 0.341 -> 0.196Hurt
MoLF versus STPath on zero-shot cross-species dataMoLF · Zero-shot mouse melanomaPCC: 0.090 -> 0.202Improved

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