Research map / Vision-language and multimodal / Robot action and navigation
AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture -of-Transformers for End-to-End Autonomous Driving
Wenhui Huang, Songyan Zhang, Qihang Huang, Zhidong Wang, Zhiqi Mao, Collister Chua, Zhan Chen, Long Chen, Chen Lv
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 diffusion-based action refiner (AR) on top of AutoMoT (ablation) | AutoMoT · Bench2Drive closed-loop | Driving Score: 87.34 -> 89.42 | Improved |
| add diffusion-based action refiner (AR) on top of AutoMoT (ablation) | AutoMoT · Bench2Drive closed-loop | Success Rate (%): 70.00 -> 74.09 | Improved |
| fine-tune VLM backbone on LingoQA and OmniDrive counterfactual data (ablation) | AutoMoT understanding expert · LingoQA | Lingo-Judge: 67.00 -> 67.20 | No clear effect |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · OmniDrive counterfactual planning | GPT score: 18.20 -> 67.80 | Improved |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · TallyQA | token accuracy: 81.40 -> 52.40 | Hurt |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · InfographicVQA | GPT score: 89.30 -> 50.20 | Hurt |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · VizWiz | GPT score: 75.60 -> 50.20 | Hurt |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · FigureQA | token accuracy: 97.60 -> 91.20 | Hurt |
| fine-tune VLM backbone on AD data (ablation) | AutoMoT understanding expert · ScienceQA | token accuracy: 88.60 -> 87.80 | No clear effect |
| use asynchronous inference with persistent KV cache instead of synchronized UE/AE (ablation) | AutoMoT · nuScenes trajectory planning | Avg L2 (m): 0.322 -> 0.324 | No clear effect |
| use asynchronous inference with persistent KV cache instead of synchronized UE/AE (ablation) | AutoMoT · Inference latency without diffusion head | total latency (ms): 117.3 -> 37.0 | Improved |
| use asynchronous inference with persistent KV cache instead of synchronized UE/AE (ablation) | AutoMoT with diffusion head · Inference latency with diffusion head | total latency (ms): 143.3 -> 63.0 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 5 on most shared results.
- ReCogDrive — ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving (ICLR 2026) · better on 2 of 3 shared results
- SimLingo — SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment (CVPR 2025) · better on 2 of 2 shared results
- Drive-R1 — Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026) · better on 0 of 1 shared result
- 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
- ORION — ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation (ICCV 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
- AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning (NeurIPS 2025 · similarity 0.93)
- Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning (AAAI 2026 · similarity 0.92)
- LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving (NeurIPS 2026 · similarity 0.92)
- SOLVE: Synergy of Language-Vision and End-to-End Networks for Autonomous Driving (CVPR 2025 · similarity 0.91)
- Less Language, More Latents: Annotation-Efficient VLAs for Driving (NeurIPS 2026 · similarity 0.91)
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving (NeurIPS 2026 · similarity 0.91)
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.
