mlsanityData to 7 Oct 2026

ScDiVa: Masked Discrete Diffusion for Joint Modeling of Single-Cell Identity and Expression

arXiv 2602.03477 ↗First posted 3 Feb 2026cs.LG cs.AI q-bio.GNcited by 0

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Single-cell RNA-seq profiles are high-dimensional, sparse, and unordered, causing autoregressive generation to impose an artificial ordering bias and suffer from error accumulation. To address this, we propose scDiVa, a masked discrete diffusion foundation model that aligns generation with the dropout-like corruption process by defining a continuous-time forward masking mechanism in token space. ScDiVa features a bidirectional denoiser that jointly models discrete gene identities and continuous values, utilizing entropy-normalized serialization and a latent anchor token to maximize information efficiency and preserve global cell identity. The model is trained via depth-invariant time sampling and a dual denoising objective to simulate varying sparsity levels while ensuring precise recovery of both identity and magnitude. Pre-trained on 59 million cells, scDiVa achieves strong transfer performance across major benchmarks, including batch integration, cell type annotation, and perturbation response prediction. These results suggest that masked discrete diffusion serves as a biologically coherent and effective alternative to autoregression.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 13 of its 41 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

13 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024scDiffusion: conditional generation of high-quality single-cell data using diffusion model8 Jan

Other references · 12

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  3. 2020GLU Variants Improve Transformercited by 1,724
  4. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  5. 2019Root Mean Square Layer Normalizationcited by 1,425
  6. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  7. 2025Large Language Diffusion Modelscited by 872
  8. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  9. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 606
  10. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  11. 2022Continuous diffusion for categorical datacited by 202
  12. 2021Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognitioncited by 143

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024scRDiT: Generating single-cell RNA-seq data by diffusion transformers and accelerating sampling
  2. 2026Improving scDiffusion with Sparsity-Biased Classifier-Free Guidance
  3. 2025Doloris: Dual Conditional Diffusion Implicit Bridges with Sparsity Masking Strategy for Unpaired Single-Cell Perturbation Estimation
  4. 2025Clustering by Denoising: Latent plug-and-play diffusion for single-cell data
  5. 2026Lingshu-Cell: A generative cellular world model for transcriptome modeling toward virtual cells
  6. 2026D2R2: Discrete Diffusion with Regulation Reinforcement for Single-Cell Perturbation Prediction
  7. 2025LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
  8. 2025Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion