AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models

Mingchen Song, Xiang Deng, Jie Wei, Dongmei Jiang, Liqiang Nie, Weili Guan

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Accelerated diffusion policies · 3 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 spatial energy constraint (ablation)EnergyAction · RLBench2 (20 demos)average success rate: 76.6 -> 77.3Improved
add temporal energy constraint (ablation)EnergyAction · RLBench2 (20 demos)average success rate: 76.1 -> 77.3Improved
add temporal and spatial energy to composition (ablation)E-Compose · RLBench2 (20 demos)average success rate: 73.4 -> 77.3Improved
add energy-based composition and coordination (ablation)Base policy · RLBench2 (20 demos)average success rate: 35.1 -> 77.3Improved
add energy components at 100 demos (ablation)Base policy · RLBench2 (100 demos)average success rate: 50.5 -> 86.4Improved
add energy components at 5 demos (ablation)Base policy · RLBench2 (5 demos)average success rate: 15.2 -> 44.6Improved
use Flow Matching instead of DDIM for both arms (ablation)EnergyAction · RLBench2 (20 demos)average success rate: 75.3 -> 77.3Improved
use Flow Matching instead of DDPM for both arms (ablation)EnergyAction · RLBench2 (20 demos)average success rate: 76.2 -> 77.3No clear effect
use DDIM instead of Flow Matching for both arms at 100 demos (ablation)EnergyAction · RLBench2 (100 demos)average success rate: 86.4 -> 82.1Hurt
use adaptive denoising instead of fixed 5-step denoising (ablation)EnergyAction · RLBench2mean denoising steps: 5 -> 1.79 and 1.27Improved
use early stop denoising instead of fixed 5-step denoising (ablation)EnergyAction · RLBench2mean denoising steps: 5 -> 2.13 and 2.32Improved
add energy composition without any single-arm pretraining versus 3DFA (ablation)EnergyAction · RLBench2 (20 demos), 0 single-arm taskssuccess rate: 44.8 -> 52.3Improved

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