AI Paper Atlas

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

Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight

Yifei Dong, Fengyi Wu, Guangyu Chen, Lingdong Kong, Xu Zhu, Qiyu Hu, Yuxuan Zhou, Jingdong Sun, Jun-Yan He, Qi Dai, Alexander Hauptmann, Zhi-Qi Cheng

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents

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 intra-step memory (ablation)UniWM · Go StanfordSuccess Rate: 0.71 -> 0.73Improved
add cross-step memory on top of intra-step memory (ablation)UniWM · ReConSuccess Rate: 0.85 -> 0.93Improved
add both memory banks (ablation)UniWM · HuRoNSuccess Rate: 0.70 -> 0.76Improved
train planner and world model jointly instead of separately (ablation)UniWM · Navigation avgSuccess Rate: 0.65 -> 0.71Improved
train planner and world model jointly instead of separately (ablation)UniWM · Visualization avgSSIM: 0.443 -> 0.457Improved
interleave planner and world-model substeps instead of predicting both (ablation)UniWM · Go StanfordSuccess Rate: 0.65 -> 0.71Improved
use 1 x 784 tokens instead of 2 x 484 tokens (ablation)UniWM · Navigation avg (no memory)Success Rate: 0.55 -> 0.71Improved
use 2 x 625 tokens instead of 1 x 784 tokens (ablation)UniWM · Navigation avg (no memory)Success Rate: 0.71 -> 0.68Hurt
use 5 memory layers instead of 32 (ablation)UniWM · Go StanfordSuccess Rate: 0.58 -> 0.75Improved
use 5 memory layers instead of 3 (ablation)UniWM · Go StanfordATE: 0.27 -> 0.22Improved
use 7 memory layers instead of 5 (ablation)UniWM · SCANDSuccess Rate: 0.68 -> 0.69Mixed
add goal conditioning in visualization substep (ablation)UniWM · TartanDrive (zero-shot)Success Rate: 0.33 -> 0.35Improved

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