AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Primary-Fine Decoupling for Action Generation in Robotic Imitation

Xiaohan Lei, Min Wang, Wengang Zhou, Xingyu Lu, Houqiang Li

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 1 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 mode-conditioned MeanFlow policy on top of primary mode policy (ablation)PF-DAG without MeanFlow · Adroit/DexArt/MetaWorld weightedweighted success: 0.01 -> 0.72Improved
add primary mode policy (ablation)PF-DAG without primary mode · Adroit/DexArt/MetaWorld weightedweighted success: 0.56 -> 0.72Improved
use K=64 modes instead of 8 (ablation)PF-DAG · Adroit/DexArt/MetaWorld weightedweighted success: 0.61 -> 0.72Improved
use K=64 modes instead of 1024 (ablation)PF-DAG · Adroit/DexArt/MetaWorld weightedweighted success: 0.58 -> 0.72Improved
use K=64 instead of 16, 32 or 128 (ablation)PF-DAG · Adroit/DexArt/MetaWorld weightedweighted success: 0.70 -> 0.72No clear effect
use VQ-VAE instead of k-means tokenization (ablation)PF-DAG · Adroit/DexArt/MetaWorld weightedweighted success: 0.70 -> 0.72No clear effect
replace CFM with MeanFlow (1-NFE) (ablation)PF-DAG · Adroit/DexArt/MetaWorld weightedsuccess rate: 0.69 -> 0.72Improved
use 10-NFE Euler or Runge-Kutta instead of 1-NFE Euler for CFM (ablation)CFM variant · Adroit/DexArt/MetaWorld weightedsuccess rate: 0.69 -> 0.69, 0.69 -> 0.68No clear effect
use PF-DAG instead of DP3 on real-world Wipe TablePF-DAG · Wipe Table (real world)total jerk: 1.25 -> 0.45Improved
increase number of function evaluations at inference (ablation)PF-DAG · Simulation benchmarkssuccess rateNo clear effect
use PF-DAG instead of DP3 on MetaWorld Hard (5)PF-DAG · MetaWorld Hard (5)success rate: 0.35 -> 0.72Improved

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