AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Predicting Consequences and Reinforcing Navigation Policies with Latent World Models

Zengmao Wang, Wei Gao, Shuhan Shen

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents · 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 counterfactual action sequences (M=16 vs M=1) (ablation)LWM-B-P · SCANDACC3: 34.19 -> 70.46Improved
add counterfactual action sequences (M=16 vs M=1) (ablation)LWM-B-P · SCANDposition error (PE): 2.239 -> 0.890Improved
increase counterfactual sequences from M=1 to M=2 (ablation)LWM-B-P · SCANDACC5: 23.83 -> 44.55Improved
increase counterfactual sequences from M=8 to M=16 (ablation)LWM-B-P · SCANDACC5: 46.11 -> 58.54Improved
add counterfactual action sequences (M=2 vs M=1) (ablation)LWM-S · LWM datasetACC3: 43.96 -> 89.36Improved
increase counterfactual sequences beyond M=4 (ablation)LWM-S · LWM datasetACC3: 88.46 -> 87.20No clear effect
add counterfactual action sequences (M=2 vs M=1) (ablation)LWM-B-P · LWM datasetposition error (PE): 5.205 -> 3.586Improved
increase counterfactual sequences beyond M=4 (ablation)LWM-B-P · LWM datasetACC3: 62.88 -> 61.26No clear effect
use MSE with log label instead of contrastive loss (ablation)LWM-B-P · LWM datasetACC3: 36.00 -> 90.60Improved
use MSE with log label instead of plain MSE (ablation)LWM-B-P · LWM datasetACC3: 86.40 -> 90.60Improved
use MSE with log label instead of contrastive and ranking loss (ablation)LWM-B-P · LWM datasetACC3: 85.40 -> 90.60Improved
provide goal prompt in advance (LWM-B-P vs LWM-B) (ablation)LWM-B · SCANDACC3: 58.03 -> 83.93Improved

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