AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

Yun He, Francesco Pittaluga, Ziyu Jiang, Matthias Zwicker, Manmohan Chandraker, Zaid Tasneem

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 5 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 Behavior Reviewer feedback loop (ablation)LangDriveCTRL behavior editing · Multi-object behavior instructions (70)overall success (%): 34.29 -> 51.43Improved
add counterfactual behavior generation (ablation)Behavior Editing Agent · Multi-object behavior instructions (70)overall success (%): 47.14 -> 51.43Improved
add counterfactual behavior generation to reject infeasible instructions (ablation)Behavior Editing Agent · Unreasonable instructions (30)rejection rate (%): 0.00 -> 93.33Improved
apply video diffusion tool once to coarse render (ablation)LangDriveCTRL rendering · Insertion/replacement (video refinement ablation)FID: 43.54 -> 36.83Improved
apply video diffusion tool once to coarse render (ablation)LangDriveCTRL rendering · Insertion/replacement (video refinement ablation)appearance alignment (%): 87.69 -> 65.47Hurt
add Video Reviewer Agent on top of diffusion tool (ablation)LangDriveCTRL rendering · Insertion/replacement (video refinement ablation)appearance alignment (%): 65.47 -> 85.28Improved
add Video Reviewer Agent on top of diffusion tool (ablation)LangDriveCTRL rendering · Insertion/replacement (video refinement ablation)FID: 36.83 -> 36.78No clear effect
video diffusion refinement of coarse render (ablation)LangDriveCTRL · Waymo hallucination analysis3D consistency: 74.07 -> 72.64Hurt
use coarse scene-graph render without diffusion vs ChatSim (ablation)LangDriveCTRL (Coarse) · Waymo editing (30 scenes)behavior alignment (%): 26.64 -> 73.18Improved
add edited frames to real training dataBEVFormer · Waymo BEVFormer detectionAP@0.5: 0.0533 -> 0.0635Improved
use VLM-based Object Grounding Agent instead of Grounding SAMobject query · Object grounding (50 queries)accuracy (%): 44.00 -> 84.00Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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