Learned Relay Representations for Forward-Thinking Discrete Diffusion Models
When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information stored as model representations. To avoid a hard reset between denoising rounds, we propose Learned Relay Representations (Relay), a method that allows MDMs to be forward-thinking when denoising by explicitly learning how to propagate latent information for the benefit of future denoising steps. Relay introduces a differentiable per-token channel that passes information between forward passes and is trained via truncated backpropagation through time (BPT...
| Authors | Benjamin Rozonoyer, Jacopo Minniti, Dhruvesh Patel et al. |
|---|---|
| Primary category | cs.LG |
| Published | 21 May 2026 |
| Last updated at source | 28 September 2026 |
Connected in the knowledge graph
- brozonoyer/sudoku-extreme-multi-solutionDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.