AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 152 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 multi-view joint prediction (wrist view) (ablation)Ctrl-World · DROID val, wrist-viewFVD: 158.1 -> 127.1Improved
add frame-level action conditioning (ablation)Ctrl-World · DROID val, wrist-viewFVD: 179.1 -> 127.1Improved
add frame-level action conditioning (ablation)Ctrl-World · DROID val, third-viewFVD: 122.7 -> 97.4Improved
add pose-conditioned memory retrieval (ablation)Ctrl-World · DROID val, third-viewFVD: 105.5 -> 97.4Improved
add pose-conditioned memory retrieval (ablation)Ctrl-World · DROID val, wrist-viewFVD: 133.1 -> 127.1Improved
use multi-view prediction instead of single-viewCtrl-World · DROID val, third-viewFVD: 127.5 -> 97.4Improved
use multi-view prediction instead of single-viewCtrl-World · DROID val, third-viewFID: 23.47 -> 25.00Hurt
Ctrl-World-Single-View vs IRASim-Single-Viewsingle-view world model · DROID val, third-viewPSNR: 21.36 vs 21.27Mixed
post-train pi0.5 on world-model synthetic successful trajectoriespi0.5-DROID · novel instructions and objectssuccess rate (%): 38.7 -> 83.4Improved
post-train on synthetic datapi0.5-DROID · Towel folding with directionssuccess rate: 0.575 -> 0.80Improved
evaluate policies in world model instead of real worldCtrl-World · Drawer and Close-laptop success ratesuccess rate: 0.80 -> 0.30 (Drawer, pi0.5); 0.70 -> 0.05 (Close-laptop, pi0.5)Hurt

Later papers that compared with this method

2 later accepted papers report Ctrl-World as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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