AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Lifting Ego World Models for Planning and Control

Alex Wang, Trevor Darrell, Pavel Izmailov, Yutong Bai, Amir Bar

ECCV 2026 · Reinforcement learning › Visual and representation RL · approach: Vision-based robot RL

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 waypoint conditioning (ablation)NoMaD-like policy with pose context · Nymeria policy validationgoal-conditioned all-joint MJE (m): 0.323 -> 0.243Improved
add pose context (ablation)NoMaD-like policy · Nymeria policy validationgoal-conditioned all-joint MJE (m): 0.367 -> 0.323Improved
add architecture changes (DINOv3, larger UNet) (ablation)NoMaD-like policy · Nymeria policy validationgoal-conditioned all-joint MJE (m): 0.392 -> 0.367Improved
add goal observation conditioning to NoMaD baseline (ablation)NoMaD-like policy · Nymeria policy validationMJE reduction: 2.1cm -> 1.3cmNo clear effect
remove goal masking in policy training (ablation)waypoint-conditioned policy · Nymeria policy validationgoal-conditioned all-joint MJE (m): 0.243 -> 0.226Mixed
add depth to waypoints (3D conditioning) (ablation)waypoint-conditioned policy · Nymeria policy validationgoal-conditioned all-joint MJE (m): 0.243 -> 0.226No clear effect
plan with Lifted CEM (2D waypoints) instead of PEVA CEM in joint spacePEVA world model · Nymeria planning (128 tasks, CEM)all-joint MJE (m): 0.616 -> 0.374Improved
search 3D waypoints instead of 2D waypoints in CEM (ablation)Lifted CEM · Nymeria planning (128 tasks, CEM)all-joint MJE (m): 0.374 -> 0.420Hurt
plan with Lifted CEM instead of goal-image policies (NoMaD, HDP)PEVA world model · Nymeria planning (128 tasks, CEM)all-joint MJE (m): 0.512 -> 0.374Improved
plan with lifted world model on unseen environmentsLifted CEM · Nymeria planning, unseen environmentsall-joint MJE (m): 0.553 -> 0.362Improved
lift DexWM with waypoints for planningDexWM · EgoDex planning with DexWM (256 tasks)all-joint MJE (cm): 13.81 -> 7.98Improved
add waypoint masking in policy training (ablation)Lifted CEM · Nymeria planning (64 tasks)leaf MJE (m): 0.399 -> 0.388Improved

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