AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning

Kangye Ji, Jianbo Zhou, Yuan Meng, Ye Li, Hanyun Cui, Zhi Wang

ICML 2026 · Image generation › Fast diffusion sampling · approach: Accelerated diffusion policies · 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
replace the real-time observation-conditioned pruner with a fixed pruning schedule (ablation)SAG · Average over 10 taskssuccess rate (%): 87 -> 83Hurt
add one-for-all reusing instead of block-wise reusing (ablation)SAG · Average over 10 taskssuccess rate (%): 74 -> 87Improved
add global sparsity loss instead of block-wise uniform loss (ablation)SAG · Average over 10 taskssuccess rate (%): 53 -> 87Improved
add sinusoidal positional encoding to the pruner (ablation)SAG · Robomimic Tool Hangsuccess rate (%): 28 -> 54Improved
raise target pruning rate from 91% to 97% (ablation)SAG · Average over 10 taskssuccess rate (%): 85 -> 51Hurt
lower target pruning rate from 91% to 80% (ablation)SAG · Average over 10 taskssuccess rate (%): 85 -> 85No clear effect
combine SAG with DPM-Solver++ 50 stepsDPM50 · Robomimic MH Squaresuccess rate (%): 72 -> 78Improved
use fixed caching schedule instead of rollout-adaptive pruning (EfficientVLA)DP-T · Franka Kitchen p4success rate (%): 99 -> 0Hurt
apply SAG to DP-T on real-world Assembly LineDP-T · Real-world Assembly Linesuccess rate (%): 26 -> 58Improved
apply SAG to DP-T on real-world Stack BowlsDP-T · Real-world Stack Bowlssuccess rate (%): 82 -> 78No clear effect

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