AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence Extrapolation

Zekai Li, Ji Liu, Yiqing Huang, Ziqiong Liu, Dong Li, Emad Barsoum

ICML 2026 · Image generation › Fast diffusion sampling · approach: Masked diffusion language model decoding · 0 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 TSPD trace-aware controller (ablation)TSPD+CE · GSM8K, gen len 256speedup: 2.9× -> 5.0×Improved
add Confidence Extrapolation (ablation)TSPD · GSM8K, gen len 256speedup: 4.4× -> 5.0×Improved
add CE to other controllers (ablation)Learn2PD, Fast-dLLM, Credit Decoding · GSM8K, gen len 256speedup: Learn2PD 4.2× -> 4.7×; Fast-dLLM 7.8× -> 9.3×; CD 7.9× -> 8.4×Improved
add CE (ablation)TSPD · GSM8K, gen len 256accuracy: 79.5 -> 79.4No clear effect
add confidence feature to TSPD (ablation)TSPD · GSM8K, gen len 256speedup: 2.8× -> 4.4×Improved
add entropy feature to TSPD (ablation)TSPD · GSM8K, gen len 256speedup: 4.1× -> 4.4×Improved
add momentum feature to TSPD (ablation)TSPD · GSM8K, gen len 256speedup: 4.3× -> 4.4×Improved
add position feature to TSPD (ablation)TSPD · GSM8K, gen len 256accuracy: 78.5 -> 79.5Improved
add position feature to TSPD (ablation)TSPD · GSM8K, gen len 256speedup: 4.5× -> 4.4×Hurt
use 2-layer LSTM instead of MLP or deeper LSTM (ablation)TSPD controller · GSM8K, gen len 256accuracy: 2-layer MLP 78.8 -> 2-layer LSTM 79.5Improved
add Dual Cache (ablation)TSPD+CE · GSM8K, gen len 256speedup: 5.0× -> 11.2×Improved
add Prefix Cache (ablation)TSPD+CE · GSM8K, gen len 256speedup: 5.0× -> 5.4×Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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