# SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention

arXiv: https://arxiv.org/abs/2604.16776 · HTML: https://mlsanity.com/paper/2604.16776/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 41 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Understanding and Improving Layer Normalization](https://mlsanity.com/paper/1911.07013/) (2019)
- [Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold](https://mlsanity.com/paper/2408.14608/) (2024)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [scDiffusion: conditional generation of high-quality single-cell data using diffusion model](https://mlsanity.com/paper/2401.03968/) (2024)
- [Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen](https://mlsanity.com/paper/2407.11734/) (2024)

## Abstract (arXiv)

Modeling single-cell gene expression across diverse biological and technical conditions is crucial for characterizing cellular states and simulating unseen scenarios. Existing methods often treat genes as independent tokens, overlooking their high-level biological relationships and leading to poor performance. We introduce SAVE, a unified generative framework based on conditional Transformers for multi-condition single-cell modeling. SAVE leverages a coarse-grained representation by grouping semantically related genes into blocks, capturing higher-order dependencies among gene modules. A Flow Matching mechanism and condition-masking strategy further enhance flexible simulation and enable generalization to unseen condition combinations. We evaluate SAVE on a range of benchmarks, including conditional generation, batch effect correction, and perturbation prediction. SAVE consistently outperforms state-of-the-art methods in generation fidelity and extrapolative generalization, especially in low-resource or combinatorially held-out settings. Overall, SAVE offers a scalable and generalizable solution for modeling complex single-cell data, with broad utility in virtual cell synthesis and biological interpretation. Our code is publicly available at https://github.com/fdu-wangfeilab/sc-save