Lossy Compressive Text Autoencoders
arXiv:2610.10738v1 Announce Type: new Abstract: Our work explores learning a compressed latent representation of text, at the intersection of data compression and representation learning. We propose an autoencoder architecture that performs residual downscaling and upscaling of hidden representatio…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-09 04:00 · arXiv cs.CL
Lossy Compressive Text Autoencoders