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.
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.
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.
More in Research
All →- Study finds token-level entropy blind in small language models, semantic entropy helps · 1 src
- Researchers propose AI-GRACE framework for operationalizing agentic AI use cases · 1 src
- Embed‑TTT improves rule induction in ARC‑like tasks, authors say · 1 src
- Researchers introduce SpecOpt for agentic molecule specificity optimization · 1 src
- researchers report agent-based hls with rtl refinement speeds chip design 2.6× · 1 src
Comments
via GitHub Discussions