AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

CUBic: Coordinated Unified Bimanual Perception and Control Framework

Xingyu Wang, Pengxiang Ding, Jingkai Xu, Donglin Wang, Zhaoxin Fan

CVPR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 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 shared mapping for dual codebooks (ablation)CUBic · RoboTwinmean success rate (%): 40.1 -> 51.8Improved
add two-stage training (single-arm pre-training then dual-arm post-training) (ablation)CUBic · RoboTwinmean success rate (%): 42.1 -> 51.8Improved
add both shared mapping and two-stage training (ablation)CUBic · RoboTwinmean success rate (%): 32.6 -> 51.8Improved
add shared mapping without two-stage training (ablation)CUBic · RoboTwinmean success rate (%): 32.6 -> 42.1Improved
add two-stage training without shared mapping (ablation)CUBic · RoboTwinmean success rate (%): 32.6 -> 40.1Improved
add latent tokens (N=4) before quantization (ablation)CUBic · RoboTwinmean success rate (%): 0.0 -> 51.8Improved
use more latent tokens and larger codebook (N=8, K=512 vs N=4, K=256) (ablation)CUBic · RoboTwinmean success rate (%): 51.8 -> 40.2Hurt
replace DP with CUBicDiffusion Policy · RoboTwin (7 tasks average)success rate (%): 38.5 -> 51.8Improved
replace DP3 (with point clouds) with RGB-only CUBicDP3 · RoboTwin (7 tasks average)success rate (%): 39.8 -> 51.8Improved
replace DP with CUBicDiffusion Policy · Dual Bottles Pick (Easy)success rate (%): 85.7 -> 84.3No clear effect
replace DP3 with CUBicDP3 · Dual Shoes Placesuccess rate (%): 12.0 -> 10.0No clear effect
replace DP with CUBic on real robot in-domainDiffusion Policy · Real-world in-domainstep-wise score: 19.5 -> 43.1Improved

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