DigestAI news desk

AI news, digested. Every story with its sources, every hour.

Research

reviser proposes cursor-based text generation

Reviser is a decoder‑only Transformer that generates text as a sequence of cursor‑relative actions on a mutable canvas. At each step it predicts one of three tokens: INSERT(token), MOVE(Δ), or STOP, making the model autoregressive over edit history rather than final text order.

1 source primary source

Key points

  • Reviser is a decoder‑only Transformer that uses cursor‑relative actions to generate text
  • It outperforms SEDD and MDLM on a continuation benchmark and performs frequent backward moves
  • It requires less inference compute than multi‑pass refinement and diffusion‑style baselines

On a continuation benchmark, Reviser is strongly preferred to SEDD and MDLM in arena evaluations, and trajectory statistics show frequent backward moves and mid‑canvas insertions. Compared to size‑matched autoregressive baselines, Reviser performs competitively at both 100M and 300M parameter scales. Under a shared FLOPs convention, it also requires substantially less inference compute than multi‑pass refinement and diffusion‑style baselines.

Read the original atarXiv cs.CL · by Sean Diab primary sourceOpen source ↗
Topics · follow one to build your own front page
Reviser

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us.

Comments

via GitHub Discussions

More in Research

All →

Related stories