Skip to content

Author

M. Parwani

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

Adaptive Multi-Token Prediction: How far should we go?

Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amortization when reliable, but can waste compute on suffixes discarded after a rejecti...

E. Anand, M. Parwani, Xin-Yuan Cao · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.