SPOT Speeds Up Diffusion Language Models Up to 6.8x via Commit-Order Prediction
Eliezer Shlomi · hf · 2026-10-28
Eliezer Shlomi released SPOT, a speculative decoding method for diffusion language models.
- Instead of denoising all tokens blindly, the model predicts the commit order of tokens and verifies candidates in parallel.
- Results: up to 6.8x fewer forward passes while maintaining exact decoding (output distribution unchanged).
- Benchmarked against Draft-free and Spiffy baselines on SDAR-8B / GSM8K.
An adaptation of speculative decoding ideas to the diffusion paradigm.
More from Research
- Researcher admits SETH/CSETH mixup, revises odds in P vs NP debate to >80% on CSETH — geoffreyirving · 2026-10-28
- Softmax's standard implementations hide two numerical bugs, Google paper shows — srush_nlp · 2026-10-28
- Percy Liang: experts rate 1/3 of AI-proposed research questions genuinely interesting — StanfordAILab · 2026-10-28
- Protenix team spins out Molence Bio, releases open biomolecular model Mol-1 — LeoTZ03 · 2026-10-28
- Just Action Model: decoupling what separates VLA from world-action models — Yonghao Yu · 2026-10-28
- HABIT-Bench: Best agent memory system scores just 33.61% at inferring user habits — SJTU · 2026-10-28