Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

arXiv:2609.00355v2 Announce Type: replace Abstract: Speculative decoding accelerates generation without changing its output, but on vision-language models (VLMs) a self-reinforcing cycle holds it back. Because an autoregressive drafter pays a…

Read the full story at arXiv cs.AI ↗