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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add future RGB image generation (ablation) | ExploreVLA Stage 1 · NAVSIM v1 navtest | PDMS: 86.2 -> 87.9 | Improved |
| add future depth image generation (ablation) | ExploreVLA Stage 1 · NAVSIM v1 navtest | PDMS: 86.2 -> 87.8 | Improved |
| add both RGB and depth generation (ablation) | ExploreVLA Stage 1 · NAVSIM v1 navtest | PDMS: 86.2 -> 88.5 | Improved |
| add PDMS-reward GRPO post-training (ablation) | ExploreVLA · NAVSIM v1 navtest | PDMS: 88.50 -> 90.19 | Improved |
| add image exploration reward alone (ablation) | ExploreVLA · NAVSIM v1 navtest | PDMS: 88.50 -> 88.53 | No clear effect |
| add image exploration reward to PDMS reward (ablation) | ExploreVLA · NAVSIM v1 navtest | PDMS: 90.19 -> 90.36 | Improved |
| raise safety threshold from 0.0 to 0.9 (ablation) | ExploreVLA · NAVSIM v1 navtest | PDMS: 90.25 -> 90.36 | Improved |
| raise safety threshold from 0.3 to 0.9 (ablation) | ExploreVLA · NAVSIM v1 navtest | PDMS: 90.21 -> 90.36 | Improved |
| use best-of-N (N=6) selection | ExploreVLA · NAVSIM v1 navtest | PDMS: 90.4 -> 93.7 | Improved |
| use uncertainty-based exploration bonus instead of L2 distance as novelty | ExploreVLA · 1000 straight-driving scenes | novelty measure: 0.04 +- 0.03 -> 0.29 +- 0.12 | Improved |
| ExploreVLA vs DriveVLA-W0 on NAVSIM v2 | ExploreVLA · NAVSIM v2 navtest | EPDMS: 86.1 -> 88.8 | Improved |
| ExploreVLA zero-shot closed-loop vs UniAD on Waymo | ExploreVLA · HUGSIM Waymo | HD-Score: 0.581 -> 0.360 | Hurt |
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.
- DriveVLA-W0 — DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving (ICLR 2026) · better on 2 of 2 shared results
- AutoVLA — AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025) · better on 1 of 1 shared result
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
- DriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving (ICML 2026 · similarity 0.93)
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.92)
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026 · similarity 0.90)
- From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving (NeurIPS 2026 · similarity 0.90)
- LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving (NeurIPS 2026 · similarity 0.90)
- Generative Scenario Rollouts for End-to-End Autonomous Driving (NeurIPS 2026 · similarity 0.90)
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.
