Newest papers

ReAnchor: Reusing Rejected Verifier States for Diffusion Drafting

Sanghyun Lee, 남원진, Seungho Jang, Jaeho Lee, Jiho Park, Jaewoon Lee, Seungryong Kim · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26531 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los dibujantes de difusión de bloques aceleran la decodificación especulativa generando tokens de dibujo múltiples en un solo paso adelante. Sin embargo, cada paso produce solo un bloque de longitud fija de un único ancla generado por el objetivo, limitando hasta qué punto el dibujo puede extenderse. Mientras tanto, la verificación del objetivo calcula los estados ocultos incluso en posiciones más allá del primer rechazo, pero estos estados suelen ser descartados en lugar de reutilizados. Proponemos ReAnchor, un método sin entrenamiento que reanchora un dibujante pretrainado en posiciones desplazadas utilizando estados de verificación descartados para generar bloques de dibujo paralelos. Estos bloques mejoran las predicciones dentro del bloque original y la cobertura extendida más allá de su punto final. A

Machine translation (Meta M2M100); the English original follows.

Abstract

Block diffusion drafters accelerate speculative decoding by generating multiple draft tokens in a single forward pass. However, each pass produces only a fixed-length block from a single target-generated anchor, limiting how far the draft can extend. Meanwhile, target verification computes hidden states even at positions beyond the first rejection, but these states are typically discarded rather than reused. We propose ReAnchor, a training-free method that reanchors a pretrained drafter at shifted positions using discarded verifier states to generate parallel draft blocks. These blocks improve predictions within the original block and extend coverage beyond its endpoint. At sampling temperature of T=0, ReAnchor achieves its largest average gains on Gemma 4-12B, improving acceptance length by 19.4% and decoding speed by 17.9% across eight benchmarks. Averaged equally over four target models and eight benchmarks, it improves acceptance length by 15.2% and decoding speed by 13.4% with pretrained DFlash drafters.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Decoding methods, Computer science, Block (permutation group theory), Reuse, Limiting, Algorithm

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange