#Speculative Decoding
Research
Feedback Shortcut: Speculative Decoding for Latent Feedback Transformers
Benhao Huang, Xuezhe Ma, Hector Liu
Nov 20th 2026
Institute of Foundation Models
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.
