Elucidating the Design Space of Flow Matching for Cellular Microscopy

• URL: http://arxiv.org/abs/2603.26790v1
• Date: Wed, 25 Mar 2026 15:18:37 GMT
• Title: Elucidating the Design Space of Flow Matching for Cellular Microscopy
• Abstract summary: Flow-matching generative models are increasingly used to simulate cell responses to biological perturbations.<n>We systematically analyse the design space of flow matching models for cell-microscopy images.<n>We develop a simple, stable, and scalable recipe which we use to train our foundation model.
• Score: 4.650661110906399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Flow-matching generative models are increasingly used to simulate cell responses to biological perturbations. However, the design space for building such models is large and underexplored. We systematically analyse the design space of flow matching models for cell-microscopy images, finding that many popular techniques are unnecessary and can even hurt performance. We develop a simple, stable, and scalable recipe which we use to train our foundation model. We scale our model to two orders of magnitude larger than prior methods, achieving a two-fold FID and ten-fold KID improvement over prior methods. We then fine-tune our model with pre-trained molecular embeddings to achieve state-of-the-art performance simulating responses to unseen molecules. Code is available at https://github.com/valence-labs/microscopy-flow-matching

Related papers

• Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules [62.81692030818376]
  We introduce a new learning principle for out-of-distribution flow modeling: enlarging a model's generable set to increase coverage of the valid design space.<n>We propose Active Flow Expansion (ActFlow), a continued pre-training method that employs verifier feedback to expand a pre-trained model over new valid regions.<n>Results show that ActFlow expands valid coverage far beyond the region modeled by the initial pre-trained model, significantly outperforming widely adopted synthetic flow pre-training methods.
  arXiv  Detail & Related papers  (2026-06-07T19:43:22Z)
• UCell: rethinking generalizability and scaling of bio-medical vision models [2.4469484645516837]
  We show that UCell can be trained from scratch using only a set of microscopy imaging data.<n>We also examined and confirmed the adaptability of ucell by performing a wide range of one-shot and few-shot fine tuning experiments.
  arXiv  Detail & Related papers  (2026-03-31T21:13:20Z)
• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• Generative diffusion model surrogates for mechanistic agent-based biological models [0.003897077734517544]
  The Cellular-Potts Model (CPM) is a powerful and popular framework for developing and interrogating CPMs.<n>Surrogate models may allow for the accelerated evaluation of CPMs of complex biological systems.<n>We train a generative AI surrogate classifier of a CPM used to investigate in vitro vasculogenesis.<n>Our work represents a step towards the implementation of DDPMs to develop digital twins of biological systems.
  arXiv  Detail & Related papers  (2025-05-01T08:19:51Z)
• Surrogate modeling of Cellular-Potts Agent-Based Models as a segmentation task using the U-Net neural network architecture [0.003710987587629279]
  We develop a convolutional neural network (CNN) surrogate model using a U-Net architecture that accounts for periodic boundary conditions.<n>We use this model to accelerate the evaluation of a mechanistic Cellular-Potts model used to investigate in vitro vasculogenesis.
  arXiv  Detail & Related papers  (2025-05-01T05:30:38Z)
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [84.3224556294803]
  Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. We aim to optimize downstream reward functions while preserving the naturalness of these design spaces. Our algorithm integrates soft value functions, which looks ahead to how intermediate noisy states lead to high rewards in the future.
  arXiv  Detail & Related papers  (2024-08-15T16:47:59Z)
• A Microstructure-based Graph Neural Network for Accelerating Multiscale Simulations [0.0]
  We introduce an alternative surrogate modeling strategy that allows for keeping the multiscale nature of the problem. We achieve this by predicting full-field microscopic strains using a graph neural network (GNN) while retaining the microscopic material model. We demonstrate for several challenging scenarios that the surrogate can predict complex macroscopic stress-strain paths.
  arXiv  Detail & Related papers  (2024-02-20T15:54:24Z)
• Retrieval-based Controllable Molecule Generation [63.44583084888342]
  We propose a new retrieval-based framework for controllable molecule generation. We use a small set of molecules to steer the pre-trained generative model towards synthesizing molecules that satisfy the given design criteria. Our approach is agnostic to the choice of generative models and requires no task-specific fine-tuning.
  arXiv  Detail & Related papers  (2022-08-23T17:01:16Z)
• Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
  We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
  arXiv  Detail & Related papers  (2020-10-20T08:36:51Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.