# PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling

arXiv: https://arxiv.org/abs/2602.19685 · HTML: https://mlsanity.com/paper/2602.19685/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Maximum Likelihood Training of Score-Based Diffusion Models](https://mlsanity.com/paper/2101.09258/) (2021)
- [Kernel Mean Embedding of Distributions: A Review and Beyond](https://mlsanity.com/paper/1605.09522/) (2016)
- [How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities](https://mlsanity.com/paper/2409.11654/) (2024)
- [Diffusion Generative Models in Infinite Dimensions](https://mlsanity.com/paper/2212.00886/) (2022)
- [Memorization and Regularization in Generative Diffusion Models](https://mlsanity.com/paper/2501.15785/) (2025)
- [Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation](https://mlsanity.com/paper/2506.21107/) (2025)

## Built on by (most cited first, 8 of 8)

- [PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling](https://mlsanity.com/paper/2604.13986/) (2026)
- [Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning](https://mlsanity.com/paper/2606.01042/) (2026)
- [OCOO-T : A Simple and Scalable Virtual Cell Model for Transcriptional Perturbation Response Prediction](https://mlsanity.com/paper/2606.12838/) (2026)
- [SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction](https://mlsanity.com/paper/2603.17380/) (2026)
- [Control-Anchored Residual Flow Matching Conditioned on Gene Geometry for Virtual Cell Perturbation Modeling](https://mlsanity.com/paper/2608.06824/) (2026)
- [PerturbRx: Learning Treatment-Conditioned Latent Transitions for Patient Drug Response Prediction](https://mlsanity.com/paper/2608.21349/) (2026)
- [CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling](https://mlsanity.com/paper/2609.19970/) (2026)
- [Learning Perturbation-Specific Representations through Conditional Energy Prior for Cellular Response Prediction](https://mlsanity.com/paper/2610.18456/) (2026)

## Abstract (arXiv)

Building Virtual Cells that can accurately simulate cellular responses to perturbations is a long-standing goal in systems biology. A fundamental challenge is that high-throughput single-cell sequencing is destructive: the same cell cannot be observed both before and after a perturbation. Thus, perturbation prediction requires mapping unpaired control and perturbed populations. Existing models address this by learning maps between distributions, but typically assume a single fixed response distribution when conditioned on observed cellular context (e.g., cell type) and the perturbation type. In reality, responses vary systematically due to unobservable latent factors such as microenvironmental fluctuations and complex batch effects, forming a manifold of possible distributions for the same observed conditions. To account for this variability, we introduce PerturbDiff, which shifts modeling from individual cells to entire distributions. By embedding distributions as points in a Hilbert space, we define a diffusion-based generative process operating directly over probability distributions. This allows PerturbDiff to capture population-level response shifts across hidden factors. Benchmarks on established datasets show that PerturbDiff achieves state-of-the-art performance in single-cell response prediction and generalizes substantially better to unseen perturbations. See our project page (https://katarinayuan.github.io/PerturbDiff-ProjectPage/), where code and data will be made publicly available (https://github.com/DeepGraphLearning/PerturbDiff).