View this thread on X
Feedback Shortcut: Speculative Decoding for Latent Feedback Transformers
Posted: Nov 20th 2026
TL;DR
Latent feedback breaks speculative decoding. Feedback Shortcut fixes it with MTP stand-ins and pipelined correction: 2.4–2.8× faster decoding, within 10⁻⁴ bits per byte of exact decoding.