Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
arXiv 2610.12544v1•fa7764968fb21a386a5a64209d8811e7b54f530db6c8dae1a536c802383ad9e0
Paper metadata
- arXiv ID
- 2610.12544
- Version
- v1
- Category
- cs.IT, cs.LG, math.IT, math.ST, stat.ML, stat.TH
- Authors
- Jingda Wu, Changxiao Cai
- Publication date
- 2026-10-12T04:00:00Z
- Source identifier
- 2610.12544v1
- Public record ID
- record:sha256:fa7764968fb21a386a5a64209d8811e7b54f530db6c8dae1a536c802383ad9e0
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- fa7764968fb21a386a5a64209d8811e7b54f530db6c8dae1a536c802383ad9e0
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.