AI Paper Atlas

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

ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving

Zihao Sheng, Xin Ye, Jingru Luo, Sikai Chen, Liu Ren

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 9 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 future RGB image generation (ablation)ExploreVLA Stage 1 · NAVSIM v1 navtestPDMS: 86.2 -> 87.9Improved
add future depth image generation (ablation)ExploreVLA Stage 1 · NAVSIM v1 navtestPDMS: 86.2 -> 87.8Improved
add both RGB and depth generation (ablation)ExploreVLA Stage 1 · NAVSIM v1 navtestPDMS: 86.2 -> 88.5Improved
add PDMS-reward GRPO post-training (ablation)ExploreVLA · NAVSIM v1 navtestPDMS: 88.50 -> 90.19Improved
add image exploration reward alone (ablation)ExploreVLA · NAVSIM v1 navtestPDMS: 88.50 -> 88.53No clear effect
add image exploration reward to PDMS reward (ablation)ExploreVLA · NAVSIM v1 navtestPDMS: 90.19 -> 90.36Improved
raise safety threshold from 0.0 to 0.9 (ablation)ExploreVLA · NAVSIM v1 navtestPDMS: 90.25 -> 90.36Improved
raise safety threshold from 0.3 to 0.9 (ablation)ExploreVLA · NAVSIM v1 navtestPDMS: 90.21 -> 90.36Improved
use best-of-N (N=6) selectionExploreVLA · NAVSIM v1 navtestPDMS: 90.4 -> 93.7Improved
use uncertainty-based exploration bonus instead of L2 distance as noveltyExploreVLA · 1000 straight-driving scenesnovelty measure: 0.04 +- 0.03 -> 0.29 +- 0.12Improved
ExploreVLA vs DriveVLA-W0 on NAVSIM v2ExploreVLA · NAVSIM v2 navtestEPDMS: 86.1 -> 88.8Improved
ExploreVLA zero-shot closed-loop vs UniAD on WaymoExploreVLA · HUGSIM WaymoHD-Score: 0.581 -> 0.360Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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