# Sakana AI — UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action Branching

- Company: Sakana AI (sakana.ai)
- Announced: 2026-07-22T15:00:00+00:00
- Category: research-paper
- Subject: Sakana models
- Models affected: Dream-Coder
- Source: https://sakana.ai/umf
- Record: https://forck.live/items/4674-unmaskfork-test-time-scaling-for-masked-diffusion-via-deterministic-action

Sakana AI announces its ICML 2026 paper 'UnMaskFork' which introduces a method for test-time scaling in masked diffusion language models by having multiple models collaborate through model switching and Monte Carlo Tree Search, improving performance on coding and math tasks without additional training or model changes.

## Evidence

Verbatim from https://sakana.ai/umf:

> In our ICML 2026 paper “UnMaskFork,” we show that having multiple masked diffusion language models collaborate on a single answer improves performance on coding and math tasks.

---

Record: https://forck.live/items/4674-unmaskfork-test-time-scaling-for-masked-diffusion-via-deterministic-action
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md