Pith. sign in

REVIEW 19 cited by

DriveLM: Driving with Graph Visual Question Answering

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.14150 v3 pith:ZIPLG4A4 submitted 2023-12-21 cs.CV

DriveLM: Driving with Graph Visual Question Answering

classification cs.CV
keywords drivinggraphend-to-endhumanreasoningtaskvlmsanswering
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We study how vision-language models (VLMs) trained on web-scale data can be integrated into end-to-end driving systems to boost generalization and enable interactivity with human users. While recent approaches adapt VLMs to driving via single-round visual question answering (VQA), human drivers reason about decisions in multiple steps. Starting from the localization of key objects, humans estimate object interactions before taking actions. The key insight is that with our proposed task, Graph VQA, where we model graph-structured reasoning through perception, prediction and planning question-answer pairs, we obtain a suitable proxy task to mimic the human reasoning process. We instantiate datasets (DriveLM-Data) built upon nuScenes and CARLA, and propose a VLM-based baseline approach (DriveLM-Agent) for jointly performing Graph VQA and end-to-end driving. The experiments demonstrate that Graph VQA provides a simple, principled framework for reasoning about a driving scene, and DriveLM-Data provides a challenging benchmark for this task. Our DriveLM-Agent baseline performs end-to-end autonomous driving competitively in comparison to state-of-the-art driving-specific architectures. Notably, its benefits are pronounced when it is evaluated zero-shot on unseen objects or sensor configurations. We hope this work can be the starting point to shed new light on how to apply VLMs for autonomous driving. To facilitate future research, all code, data, and models are available to the public.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs

    cs.CV 2026-04 unverdicted novelty 8.0

    CCTVBench exposes a large gap between standard QA accuracy and contrastive consistency in traffic video reasoning for multimodal LLMs and introduces C-TCD to narrow that gap.

  2. MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

    cs.CV 2024-08 conditional novelty 8.0

    MME-RealWorld is the largest manually annotated high-resolution benchmark for MLLMs, where even the best models achieve less than 60% accuracy on challenging real-world tasks.

  3. TRIP-Evaluate: An Open Multimodal Benchmark for Evaluating Large Models in Transportation

    cs.CV 2026-04 accept novelty 7.0

    TRIP-Evaluate is a new open multimodal benchmark with 837 text, image, and point-cloud items organized by a role-task-knowledge taxonomy to evaluate large models on transportation workflows.

  4. AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning

    cs.CV 2025-03 unverdicted novelty 7.0

    AlphaDrive uses GRPO-based RL rewards and two-stage SFT+RL training on VLMs to improve autonomous driving planning performance and efficiency while producing emergent multimodal capabilities.

  5. Visual Adversarial Attack on Vision-Language Models for Autonomous Driving

    cs.CV 2024-11 unverdicted novelty 7.0

    ADvLM is the first visual adversarial attack framework for VLMs in autonomous driving, using semantic-invariant induction via LLM-generated prompt libraries and scenario-associated attention-based enhancement to achie...

  6. LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

    cs.CV 2026-05 unverdicted novelty 6.0

    LocateAnything proposes Parallel Box Decoding for unified generative visual grounding and detection, paired with a 138M-sample dataset, to raise both speed and high-IoU accuracy.

  7. ChainFlow-VLA: Causal Flow Planning with Vision-Language Models

    cs.CV 2026-05 unverdicted novelty 6.0

    ChainFlow-VLA unifies autoregressive causal trajectory modes with VLM-conditioned diffusion refinement to reach 94.85 on NAVSIM v1, matching human performance.

  8. EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 6.0

    EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.

  9. EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving

    cs.CV 2026-04 unverdicted novelty 6.0

    EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.

  10. OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models

    cs.CV 2026-04 unverdicted novelty 6.0

    OneDrive unifies heterogeneous decoding in a single VLM transformer decoder for end-to-end driving, achieving 0.28 L2 error and 0.18 collision rate on nuScenes plus 86.8 PDMS on NAVSIM.

  11. Beyond the Beep: Scalable Collision Anticipation and Real-Time Explainability with BADAS-2.0

    cs.CV 2026-04 unverdicted novelty 6.0

    BADAS-2.0 scales collision anticipation with a 178k-video long-tail benchmark built via active oracle selection, 7-12x faster distilled edge models, and object-centric attention heatmaps plus VLM-based textual reasoning.

  12. OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving

    cs.CV 2025-12 unverdicted novelty 6.0

    OmniDrive-R1 boosts VLM reasoning score from 51.77% to 80.35% and answer accuracy from 37.81% to 73.62% on DriveLMM-o1 via reinforcement-driven interleaved multi-modal chain-of-thought with annotation-free grounding.

  13. B4DL: A Benchmark for 4D LiDAR LLM in Spatio-Temporal Understanding

    cs.CV 2025-08 unverdicted novelty 6.0

    B4DL provides a new benchmark, scalable data generation pipeline, and MLLM architecture for direct spatio-temporal reasoning on raw 4D LiDAR data.

  14. DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving

    cs.CV 2025-05 unverdicted novelty 6.0

    DriveMoE applies scene-specialized Vision MoE and skill-specialized Action MoE to a VLA baseline to achieve SOTA closed-loop performance on Bench2Drive.

  15. Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

    cs.CV 2024-10 conditional novelty 6.0

    Senna decouples language-based high-level planning from an LVLM with low-level trajectory prediction from an E2E model, reporting 27% lower planning error and 33% lower collisions after pre-training on DriveX and fine...

  16. DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models

    cs.CV 2024-02 unverdicted novelty 6.0

    DriveVLM adds vision-language models with scene description, analysis, and hierarchical planning modules to autonomous driving, paired with a hybrid DriveVLM-Dual system tested on nuScenes and SUP-AD datasets and depl...

  17. EponaV2: Driving World Model with Comprehensive Future Reasoning

    cs.CV 2026-05 unverdicted novelty 5.0

    EponaV2 advances perception-free driving world models by forecasting comprehensive future 3D geometry and semantic representations, achieving SOTA planning performance on NAVSIM benchmarks.

  18. OmniV2X: A Generative Foundation Planner for Efficient End-to-End Cooperative Driving

    cs.RO 2026-06 unverdicted novelty 4.0

    OmniV2X is a generative foundation planner for end-to-end cooperative driving that achieves state-of-the-art performance on DAIR-V2X-Seq using less than 10% of the fine-tune V2X dataset and less than 1% of the communi...

  19. Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving

    cs.CV 2025-06 unverdicted novelty 4.0

    Introduces structured NuScenes-S dataset and 0.9B FastDrive VLM claiming 20% higher decision accuracy and over 10x inference speedup versus larger unstructured VLMs.