AI Paper Atlas

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

Scene-Adaptive VLA: Efficient Autonomous Driving via Dynamic Layer Routing

YUJIA YANG, Quan Yuan, Fan Jiawei, Yang Li, Tiange Fu, Xiaoyuan Fu, Guiyang Luo, Jinglin Li

NeurIPS 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a scene-adaptive VLA for autonomous driving that dynamically routes inputs through layers to reduce onboard inference compute while preserving driving capability and explainability.

Problem

Large VLA models strain onboard compute during real-time autonomous driving inference, increasing energy use and limiting vehicle range, so computational overhead must be reduced without hurting driving performance or explainability.

Approach

Scene-adaptive dynamic layer routing: the model selects which layers to execute depending on the driving scene, so simple scenes use less computation. Details beyond the title and abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scene-adaptive dynamic layer routing to SimLingoSimLingo · Bench2DriveLLM TFLOPs per decision: 0.59 -> 0.27Improved
add scene-adaptive dynamic layer routing to SimLingoSimLingo · Bench2DriveDriving Score: 85.07 -> 84.87No clear effect
add scene-adaptive dynamic layer routing to SimLingoSimLingo · Bench2DriveComfortness: 33.67 -> 54.36Improved
add scene-adaptive dynamic layer routing to SimLingoSimLingo · DriveLM-hard VQA and CommentarySPICE: VQA 56.77 -> 54.91; Commentary 38.04 -> 35.37Hurt
add scene-adaptive layer routing to ORIONORION · Bench2DriveDriving Score: 77.74 -> 75.88Hurt
add scene-adaptive routing to ORIONORION · Bench2DriveLLM TFLOPs per decision: 9.07 -> 4.77Improved
set fixed 100% budget with scene-aware tokens (ablation)SimLingo+SA · Bench2DriveDriving Score: 85.07 -> 86.83Improved
reduce fixed active budget from 70% to 40% (ablation)SimLingo+SA · Bench2DriveDriving Score: 85.44 -> 78.20Hurt
add budget allocation module (vs random budget) (ablation)SimLingo+SA · Bench2Drive ablationDriving Score / avg budget: DS 83.81 -> 84.87; avg budget 60.03 -> 44.64Improved
add speed deviation token (ablation)SimLingo+SA · Bench2Drive ablationAvg. budget (%): 71.89 -> 44.64Improved
add path deviation token (ablation)SimLingo+SA · Bench2Drive ablationAvg. budget (%): 66.70 -> 44.64Improved
add scene deviation token (ablation)SimLingo+SA · Bench2Drive ablationAvg. budget (%): 54.37 -> 44.64Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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