AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

When Does Flow Matching Help Deterministic Multimodal Prediction: A Spatial Transcriptomics Study

Haoran Xu, Wei Yuan, Xiao Han

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies when flow matching helps deterministic multimodal prediction, using histology-conditioned spatial transcriptomics as the testbed and comparing it with direct regression on pathology foundation features.

Problem

Flow matching is being applied to prediction tasks whose outputs are effectively deterministic, but it is unclear why it helps when output diversity is not the objective; the study focuses on histology-conditioned spatial transcriptomics prediction, a sparse high-dimensional multimodal task.

Approach

Analyzes flow matching versus direct regression from pathology foundation features for deterministic spatial transcriptomics prediction, to explain the source of its benefit beyond generative diversity. Details beyond the abstract are not available.

Experimental setup

Baselines: direct regression

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