AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs

Shuochen Chang, Xiaofeng Zhang, Qingyang Liu, Li Niu

AAAI 2026 · Image generation › Fast diffusion sampling · approach: Masked diffusion language model decoding · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add timestep-dependent linear merge schedule (D3ToM-t) over fixed ratio (ablation)D3ToM · 7 benchmarks, retain 25% tokensaverage retention: 95.23% -> 98.12%Improved
add timestep-dependent schedule (ablation)D3ToM · 7 benchmarks, retain 10% tokensaverage retention: 95.31% -> 96.75%Improved
add timestep-dependent schedule (ablation)D3ToM · 7 benchmarks, retain 50% tokensaverage retention: 96.85% -> 98.05%Improved
use decider-guided merging instead of FastV-style pruningD3ToM · LaViDa, retain 10% tokensaverage retention: 76.34% -> 95.31%Improved
use decider-guided merging instead of VisionZipD3ToM-t · LaViDa, retain 10% tokensaverage retention: 88.68% -> 96.75%Improved
use D3ToM-t instead of VisionZip on inference costD3ToM-t · LLaVA-Bench, 10% tokensTFLOPs: 51.36 -> 79.37Hurt
use D3ToM-t instead of FastV on inference costD3ToM-t · LLaVA-Bench, 10% tokensTFLOPs: 77.14 -> 79.37No clear effect
merge visual tokens in diffusion MLLM at 10% retentionD3ToM-t · LLaVA-Benchinference time (s): 1156.65s -> 493.88sImproved
combine token merging with Prefix-DLM KV cacheD3ToM · 4 benchmarks, retain 10% tokensaverage retention: 99.7%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy