A continuous-latent diffusion language model that keeps a full-width decodable latent and adapts the denoiser (low-rank noisy input, width-calibrated noise, trajectory consistency) beats compared diffusion/continuous LMs on OpenWebText and XSum.
Text diffusion model with encoder- decoder transformers for sequence-to-sequence generation
1 Pith paper cite this work, alongside 11 external citations. Polarity classification is still indexing.
1
Pith paper citing it
11
external citations · OpenAlex
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
A continuous-latent diffusion language model that keeps a full-width decodable latent and adapts the denoiser (low-rank noisy input, width-calibrated noise, trajectory consistency) beats compared diffusion/continuous LMs on OpenWebText and XSum.