pith. sign in

arxiv: 2606.29879 · v1 · pith:5FFYFQRNnew · submitted 2026-06-29 · 💻 cs.CV · cs.AI

LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving

Chen Yang , Yuhao Wei , Ze Xu , Ziheng Zou , Shuang Liang , Delin Ouyang , Lingfeng Qi , Jie Li
show 1 more author
Guofa Li
This is my paper

Pith reviewed 2026-06-30 06:32 UTC · model grok-4.3

classification 💻 cs.CV cs.AI
keywords autonomous drivingvision-language modelsworld modelstrajectory planningforesight cascade plannerend-to-end drivingBEV featuresNAVSIM benchmark
0
0 comments X

The pith

Layer-wise world-model guidance refines coarse VLM trajectories into accurate driving plans.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops LWDrive to improve end-to-end autonomous driving by addressing the geometric and future-awareness shortcomings of direct VLM trajectory outputs. It trains the VLM with future-frame generation supervision to embed predictive scene dynamics in its hidden states. A Foresight Cascade Planner then expands candidates around the coarse VLM plan and refines them progressively across layers using temporal states, action queries, and multi-view BEV features. The result is a hybrid system that keeps high-level semantic intent while correcting spatial and motion details. Benchmark results on NAVSIM and NAVSIM-v2 are presented as evidence that the refinement step produces usable plans.

Core claim

LWDrive treats the VLM output only as an intent-aware coarse plan, expands a diverse candidate space around it, and progressively refines the candidates through a Foresight Cascade Planner. Future-frame generation supervision injects planning-relevant predictive dynamics into the VLM's internal hidden states. The planner exploits VLM features across multiple layers, integrates historical temporal states, Action-Query representations, and current-frame multi-view BEV features to refine trajectories in a coarse-to-fine manner, enabling correction of spatial positions and motion trends while preserving the high-level driving intention. A score head then selects the best refined trajectory as th

What carries the argument

Foresight Cascade Planner (FCP), which exploits multi-layer VLM features under world-model supervision to refine trajectory candidates in a coarse-to-fine sequence.

If this is right

  • Refined trajectories correct spatial positions and motion trends while preserving high-level driving intention from the VLM.
  • Trajectory refinement is grounded with multi-view scene cues from BEV features.
  • A score head evaluates refined candidates and selects the final planning output.
  • The framework achieves 92.0 on the NAVSIM benchmark and 89.6 on NAVSIM-v2.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same supervision-plus-cascade pattern could be tested on VLM planners for other robotic tasks such as manipulation or navigation.
  • If the layer-wise refinement proves stable, it may reduce the need for separate geometric post-processors in VLM-based systems.
  • Success would suggest that predictive world-model signals can be injected into existing VLMs without changing their core architecture.

Load-bearing premise

Future-frame generation supervision successfully injects planning-relevant predictive dynamics into the VLM hidden states and the cascade planner can refine candidates without introducing new spatial or motion errors.

What would settle it

If ablation experiments that remove future-frame supervision or the multi-layer cascade refinement produce equal or lower NAVSIM scores than the full model, the claim that layer-wise world-model guidance improves planning accuracy would be falsified.

Figures

Figures reproduced from arXiv: 2606.29879 by Chen Yang, Delin Ouyang, Guofa Li, Jie Li, Lingfeng Qi, Shuang Liang, Yuhao Wei, Ze Xu, Ziheng Zou.

Figure 1
Figure 1. Figure 1: Comparison of VLM planning paradigms for autonomous driving. (a) Direct VLM-to-trajectory decoding lacks fine-grained correction. (b) Single-stage VLM/backbone fusion injects VLM semantics only once. (c) LWDrive performs world-model-guided coarse-to-fine refinement. also requires fine-grained spatial accuracy, temporal consis￾tency, and physical feasibility under multi-view scene con￾straints, making direc… view at source ↗
Figure 2
Figure 2. Figure 2: Overall architecture of LWDrive. LWDrive first leverages future-frame world-model supervision to guide the VLM toward predictive scene representations and an intent-aware coarse trajectory. Based on this coarse plan, it constructs a candidate trajectory pool and progressively refines it with the Foresight Cascade Planner by integrating layer-wise foresight features, temporal states, action-query memories, … view at source ↗
Figure 3
Figure 3. Figure 3: Foresight Cascade Planner. Bridge Attention in￾jects proposal interaction, action-query memory, ego-state context, and layer-wise VLM foresight features, while BEV refinement grounds the proposals with multi-view geometric cues and predicts residual updates. and st denotes ego-state information. Different from using only the final-layer VLM feature, this cascade schedule ex￾poses the planner to representat… view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative visualization of LWDrive. For each scene, we show the current front-view image, the future frame predicted by the world-model head, the trajectory planning result projected onto the front-view image, and the corresponding BEV trajectory planning result. Method L2 (m)↓ CR (%)↓ Non-Autoregressive Methods ST-P3 (Hu et al. 2022) 2.11 0.71 VAD (Jiang et al. 2023) 1.25 1.09 Ego-MLP (Li et al. 2024b) … view at source ↗
read the original abstract

Vision-Language Models (VLMs) provide powerful semantic understanding and commonsense reasoning for End-to-End Autonomous Driving (E2E-AD) planning. However, trajectories directly generated by VLMs often encode only coarse driving intentions and remain insufficient for geometrically accurate, future-aware, and multi-view-grounded planning. To address these limitations, we develop the Layer-Wise World-Model-Guided Driving framework (LWDrive). LWDrive is a VLM planning framework that refines coarse trajectories through layer-wise world-model guidance. Instead of treating the VLM output as the final trajectory, LWDrive uses it as an intent-aware coarse plan, expands a diverse candidate space around it, and progressively refines the candidates through a Foresight Cascade Planner (FCP). Specifically, we introduce future-frame generation supervision to encourage the VLM to learn forward-looking scene representations, thereby injecting planning-relevant predictive dynamics into its internal hidden states. Built upon these world-model-supervised representations, FCP exploits VLM features across multiple layers and integrates historical temporal states, Action-Query representations, and current-frame multi-view Bird's-Eye-View (BEV) features to refine candidate trajectories in a coarse-to-fine manner. This design enables progressive correction of spatial positions and motion trends while grounding trajectory refinement with multi-view scene cues and preserving the high-level driving intention produced by the large model. Finally, a score head evaluates the refined candidates and selects the best trajectory as the final planning output. Experiments show that LWDrive achieves a score of 92.0 on the NAVSIM benchmark and 89.6 on NAVSIM-v2. Code and models will be made publicly available.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces LWDrive, a VLM-based framework for end-to-end autonomous driving planning. It treats VLM outputs as coarse intent-aware trajectories, applies future-frame generation supervision to inject predictive dynamics into hidden states, and uses a Foresight Cascade Planner (FCP) to progressively refine candidate trajectories in a coarse-to-fine manner by combining multi-layer VLM features with historical states, Action-Query representations, and multi-view BEV features. A score head then selects the final trajectory. Experiments report scores of 92.0 on NAVSIM and 89.6 on NAVSIM-v2.

Significance. If the central mechanism is validated, the work could meaningfully advance E2E-AD by showing how to retain VLM commonsense reasoning while achieving geometric and motion accuracy through world-model-guided refinement. The layer-wise cascade design and future-frame supervision are potentially generalizable ideas, but the absence of supporting analyses for representation quality limits the assessed impact.

major comments (2)
  1. [Abstract] Abstract: The reported scores of 92.0 (NAVSIM) and 89.6 (NAVSIM-v2) are presented without any baseline comparisons, ablation results, error bars, dataset statistics, or statistical significance tests, making it impossible to determine whether the gains are attributable to the proposed layer-wise world-model guidance or to other factors.
  2. [Abstract] Abstract (and method overview): No evidence is supplied that future-frame generation supervision causes VLM hidden states to encode planning-relevant predictive dynamics rather than purely semantic features. Without probing, representation similarity metrics, or controlled ablations isolating this supervision effect, the claim that FCP can reliably refine trajectories without introducing new spatial or motion errors rests on an unverified assumption.
minor comments (2)
  1. The description of candidate expansion around the coarse plan and the exact architecture of the score head should be expanded with pseudocode or a diagram for reproducibility.
  2. Clarify the precise integration of Action-Query representations within the FCP cascade and whether any additional learned parameters are introduced beyond the VLM backbone.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. The comments highlight important areas where the abstract and supporting analyses can be strengthened to better substantiate the claims. We will revise the manuscript accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The reported scores of 92.0 (NAVSIM) and 89.6 (NAVSIM-v2) are presented without any baseline comparisons, ablation results, error bars, dataset statistics, or statistical significance tests, making it impossible to determine whether the gains are attributable to the proposed layer-wise world-model guidance or to other factors.

    Authors: We agree that the abstract would benefit from additional context. The full manuscript includes baseline comparisons in the experiments section showing improvements over prior methods, along with ablations. In the revision, we will update the abstract to reference key baseline scores and the magnitude of gains, and ensure the main text explicitly includes error bars, dataset statistics, and significance tests to demonstrate attribution to the proposed components. revision: yes

  2. Referee: [Abstract] Abstract (and method overview): No evidence is supplied that future-frame generation supervision causes VLM hidden states to encode planning-relevant predictive dynamics rather than purely semantic features. Without probing, representation similarity metrics, or controlled ablations isolating this supervision effect, the claim that FCP can reliably refine trajectories without introducing new spatial or motion errors rests on an unverified assumption.

    Authors: We acknowledge that the current version lacks direct empirical validation such as probing or isolated ablations for the supervision effect. In the revised manuscript, we will add controlled ablations that isolate the future-frame generation supervision, along with representation similarity metrics or probing results where feasible, to confirm that the hidden states encode planning-relevant predictive dynamics and support the FCP refinement claims. revision: yes

Circularity Check

0 steps flagged

No circularity: additive pipeline with external supervision and refinement steps

full rationale

The paper proposes an architectural pipeline (VLM coarse plan + future-frame supervision + FCP refinement using multi-layer features) whose final output is not shown by any equation or self-citation to be definitionally equivalent to its training inputs. The future-frame loss is an external supervision signal whose effect on hidden-state geometry is an empirical claim, not a tautology. No fitted parameter is renamed as a prediction, no uniqueness theorem is imported from the authors' prior work, and the reported NAVSIM scores are benchmark measurements rather than quantities forced by internal definitions. The derivation chain therefore remains self-contained against external evaluation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are identifiable from the abstract alone; the framework description remains at the level of high-level components.

pith-pipeline@v0.9.1-grok · 5863 in / 1173 out tokens · 29023 ms · 2026-06-30T06:32:10.455143+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

75 extracted references · 21 canonical work pages · 8 internal anchors

  1. [1]

    Dauner, Daniel and Hallgarten, Marcel and Li, Tianyu and Weng, Xinshuo and Huang, Zhiyu and Yang, Zetong and Li, Hongyang and Gilitschenski, Igor and Ivanovic, Boris and Pavone, Marco and Geiger, Andreas and Chitta, Kashyap , booktitle =

  2. [2]

    2025 , eprint =

    Pseudo-Simulation for Autonomous Driving , author =. 2025 , eprint =

    2025

  3. [3]

    and Vora, Sourabh and Liong, Venice Erin and Xu, Qiang and Krishnan, Anush and Pan, Yu and Baldan, Giancarlo and Beijbom, Oscar , booktitle =

    Caesar, Holger and Bankiti, Varun and Lang, Alex H. and Vora, Sourabh and Liong, Venice Erin and Xu, Qiang and Krishnan, Anush and Pan, Yu and Baldan, Giancarlo and Beijbom, Oscar , booktitle =

  4. [4]

    2023 , howpublished =

    2023

  5. [5]

    Qwen2.5-VL Technical Report

    Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Z...

    work page internal anchor Pith review Pith/arXiv arXiv

  6. [6]

    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages =

    Deep Residual Learning for Image Recognition , author =. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition , pages =

  7. [7]

    Advances in Neural Information Processing Systems , volume =

    Attention Is All You Need , author =. Advances in Neural Information Processing Systems , volume =

  8. [8]

    Advances in Neural Information Processing Systems , volume =

    Denoising Diffusion Probabilistic Models , author =. Advances in Neural Information Processing Systems , volume =

  9. [9]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    High-Resolution Image Synthesis with Latent Diffusion Models , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  10. [10]

    Li, Zhiqi and Wang, Wenhai and Li, Hongyang and Xie, Enze and Sima, Chonghao and Lu, Tong and Yu, Qiao and Dai, Jifeng , journal =

  11. [11]

    IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

    TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving , author =. IEEE Transactions on Pattern Analysis and Machine Intelligence , volume =

  12. [12]

    Hu, Shengchao and Chen, Li and Wu, Penghao and Li, Hongyang and Yan, Junchi and Tao, Dacheng , booktitle =

  13. [13]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    Planning-Oriented Autonomous Driving , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  14. [14]

    Jiang, Bo and Chen, Shaoyu and Xu, Qing and Liao, Bencheng and Chen, Jiajie and Zhou, Helong and Zhang, Qian and Liu, Wenyu and Huang, Chang and Wang, Xinggang , booktitle =

  15. [15]

    2025 IEEE International Conference on Robotics and Automation , pages =

    SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation , author =. 2025 IEEE International Conference on Robotics and Automation , pages =

    2025

  16. [16]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  17. [17]

    , year =

    Li, Keyu and Li, Zhiqi and Lan, Shiyi and Xie, Yichen and Zhang, Ziyang and Liu, Jiaming and Wu, Zuxuan and Yu, Zehui and Alvarez, Jose M. , year =. Hydra-. 2503.12820 , archivePrefix =

    work page arXiv

  18. [18]

    2505.15111 , archivePrefix =

    Guo, Ke and Liu, Haochen and Wu, Xiaojun and Pan, Jia and Lv, Chen , year =. 2505.15111 , archivePrefix =

    work page arXiv

  19. [19]

    PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving

    Wozniak, Maciej K. and Liu, Lianhang and Cai, Yixi and Jensfelt, Patric , year =. 2507.17596 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  20. [20]

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving

    Song, Ziying and Liu, Lin and Pan, Hongyu and Liao, Bencheng and Guo, Mingzhe and Yang, Lei and Zhang, Yongchang and Xu, Shaoqing and Jia, Caiyan and Luo, Yadan , year =. 2507.04049 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  21. [21]

    Drama: An efficient end-to-end motion planner for autonomous driving with mamba

    Yuan, Chengran and Zhang, Zhanqi and Sun, Jiawei and Sun, Shuo and Huang, Zefan and Lee, Christina Dao Wen and Li, Dongen and Han, Yuhang and Wong, Anthony and Tee, Keng Peng and Ang, Marcelo H. , year =. 2408.03601 , archivePrefix =

    work page arXiv

  22. [22]

    2505.19239 , archivePrefix =

    Shi, Chen and Shi, Shaoshuai and Sheng, Kehua and Zhang, Bo and Jiang, Li , year =. 2505.19239 , archivePrefix =

    work page arXiv

  23. [23]

    Proceedings of the AAAI Conference on Artificial Intelligence , volume =

    DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning , author =. Proceedings of the AAAI Conference on Artificial Intelligence , volume =

  24. [24]

    Proceedings of the AAAI Conference on Artificial Intelligence , volume =

    DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End-to-End Autonomous Driving , author =. Proceedings of the AAAI Conference on Artificial Intelligence , volume =

  25. [25]

    2504.19580 , archivePrefix =

    Feng, Rui and Xi, Ning and Chu, Duanfeng and Wang, Rukang and Deng, Zejian and Wang, Anzheng and Lu, Liping and Wang, Jinxiang and Huang, Yanjun , year =. 2504.19580 , archivePrefix =

    work page arXiv

  26. [26]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving? , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  27. [27]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    DriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous Driving , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  28. [28]

    2024 , eprint =

    Enhancing End-to-End Autonomous Driving with Latent World Model , author =. 2024 , eprint =

    2024

  29. [29]

    End-to-end driving with online trajectory evaluation via bev world model

    Li, Yingyan and Wang, Yuqi and Liu, Yang and He, Jiawei and Fan, Lue and Zhang, Zhaoxiang , year =. End-to-End Driving with Online Trajectory Evaluation via. 2504.01941 , archivePrefix =

    work page arXiv

  30. [30]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

    Epona: Autoregressive Diffusion World Model for Autonomous Driving , author =. Proceedings of the IEEE/CVF International Conference on Computer Vision , year =

  31. [31]

    Proceedings of the IEEE/CVF International Conference on Computer Vision , pages =

    DrivingGPT: Unifying Driving World Modeling and Planning with Multimodal Autoregressive Transformers , author =. Proceedings of the IEEE/CVF International Conference on Computer Vision , pages =

  32. [32]

    Zheng, Wenzhao and Chen, Weiliang and Huang, Yuanhui and Zhang, Borui and Duan, Yueqi and Lu, Jiwen , booktitle =

  33. [33]

    2025 , eprint =

    World4Drive: End-to-End Autonomous Driving via Intention-Aware Physical Latent World Model , author =. 2025 , eprint =

    2025

  34. [34]

    2602.06521 , archivePrefix =

    Jia, Feiyang and Liu, Lin and Song, Ziying and Jia, Caiyan and Ye, Hangjun and Hao, Xiaoshuai and Chen, Long , year =. 2602.06521 , archivePrefix =

    work page arXiv

  35. [35]

    2501.14729 , archivePrefix =

    Zhou, Xinyu and Liang, Dingkang and Tu, Shuyuan and Chen, Xinyu and Ding, Yuhang and Zhang, Dong and Tan, Fei and Zhao, Hang and Bai, Xiang , year =. 2501.14729 , archivePrefix =

    work page arXiv

  36. [36]

    2023 , eprint =

    Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion , author =. 2023 , eprint =

    2023

  37. [37]

    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

    Visual Point Cloud Forecasting Enables Scalable Autonomous Driving , author =. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages =

  38. [38]

    and Liu, Yu and Li, Hongsheng , booktitle =

    Shao, Hao and Hu, Yuxuan and Wang, Letian and Song, Guanglu and Waslander, Steven L. and Liu, Yu and Li, Hongsheng , booktitle =

  39. [39]

    Tian, Xiaoyu and Gu, Junru and Li, Boyuan and Liu, Yang and Wang, Yuxuan and Zhao, Zhiyuan and Zhan, Kai and Jia, Peng and Lang, Xianpeng and Zhao, Hang , booktitle =

  40. [40]

    GPT-Driver: Learning to Drive with GPT

    Mao, Jiageng and Qian, Yuxi and Ye, Junjie and Zhao, Hang and Wang, Yue , year =. 2310.01415 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  41. [41]

    AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

    Zhou, Zewei and Cai, Tianhui and Zhao, Seth Z. and Zhang, Yun and Huang, Zhiyu and Zhou, Bolei and Ma, Jiaqi , year =. 2506.13757 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  42. [42]

    DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

    Li, Yingyan and Shang, Shuyao and Liu, Weisong and Zhan, Bing and Wang, Haochen and Wang, Yuqi and Chen, Yuntao and Wang, Xiaoman and An, Yasong and Tang, Chufeng and Hou, Lu and Fan, Lue and Zhang, Zhaoxiang , year =. 2510.12796 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  43. [43]

    2025 , eprint =

    ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving , author =. 2025 , eprint =

    2025

  44. [44]

    Sgdrive: Scene-to-goal hierarchical world cognition for autonomous driving.ArXiv, abs/2601.05640, 2026

    Li, Jingyu and Wu, Junjie and Hu, Dongnan and Huang, Xiangkai and Sun, Bin and Hao, Zhihui and Lang, Xianpeng and Zhu, Xiatian and Zhang, Li , year =. 2601.05640 , archivePrefix =

    work page arXiv

  45. [45]

    SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model

    Zhou, Zewei and Yang, Ruining and Qi, Xuewei and Guo, Yiluan and Chen, Sherry X. and Feng, Tao and Pistunova, Kateryna and Shen, Yishan and Su, Lili and Ma, Jiaqi , year =. 2604.19710 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  46. [46]

    2025 , eprint =

    Unified Vision-Language-Action Model , author =. 2025 , eprint =

    2025

  47. [47]

    FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

    Zeng, Shuang and Chang, Xinyuan and Xie, Mengwei and Liu, Xinran and Bai, Yifan and Pan, Zheng and Xu, Mu and Wei, Xing , year =. FutureSightDrive: Thinking Visually with Spatio-Temporal. 2505.17685 , archivePrefix =

    work page internal anchor Pith review Pith/arXiv arXiv

  48. [48]

    Proceedings of the AAAI Conference on Artificial Intelligence , volume =

    OpenDriveVLA: Towards End-to-End Autonomous Driving with Large Vision Language Action Model , author =. Proceedings of the AAAI Conference on Artificial Intelligence , volume =

  49. [49]

    Fu, Haoyu and Zhang, Diankun and Zhao, Zongchuang and Cui, Jianfeng and Liang, Dingkang and Zhang, Chong and Zhang, Dingyuan and Xie, Hongwei and Wang, Bing and Bai, Xiang , booktitle =

  50. [50]

    2505.19381 , archivePrefix =

    Jiang, Anqing and Gao, Yu and Sun, Zhigang and Wang, Yiru and Wang, Jijun and Chai, Jinghao and Cao, Qian and Heng, Yuweng and Jiang, Hao and Zhang, Zongzheng and Guo, Xianda and Sun, Hao and Zhao, Hao , year =. 2505.19381 , archivePrefix =

    work page arXiv

  51. [51]

    2512.11872 , archivePrefix =

    Xu, Mengwei and others , year =. 2512.11872 , archivePrefix =

    work page arXiv

  52. [52]

    DriveFine: Refining-Augmented Masked Diffusion

    Dang, Cheng and others , year =. DriveFine: Refining-Augmented Masked Diffusion. 2602.14577 , archivePrefix =

    work page arXiv

  53. [53]

    Hwang, Jyh-Jing and Xu, Runsheng and Lin, Hao and Hung, Wei-Chih and Ji, Jingwei and Choi, Kyle and Huang, Dengxin and He, Tong and Covington, Paul and Sapp, Benjamin and Zhou, Yin and Guo, Jiong and Anguelov, Dragomir and Tan, Mingxing , booktitle =

  54. [54]

    2024 , eprint =

    OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning , author =. 2024 , eprint =

    2024

  55. [55]

    2401.03641 , archivePrefix =

    Han, Wencheng and Guo, Dongqian and Xu, Cheng-Zhong and Shen, Jianbing , year =. 2401.03641 , archivePrefix =

    work page arXiv

  56. [56]

    Proceedings of the 38th International Conference on Machine Learning , pages =

    Learning Transferable Visual Models from Natural Language Supervision , author =. Proceedings of the 38th International Conference on Machine Learning , pages =

  57. [57]

    Advances in Neural Information Processing Systems , volume =

    Flamingo: A Visual Language Model for Few-Shot Learning , author =. Advances in Neural Information Processing Systems , volume =

  58. [58]

    Li, Junnan and Li, Dongxu and Savarese, Silvio and Hoi, Steven , booktitle =

  59. [59]

    Advances in Neural Information Processing Systems , volume =

    Visual Instruction Tuning , author =. Advances in Neural Information Processing Systems , volume =

  60. [60]

    Computer Vision -- ECCV 2024 , pages =

    Marcu, Ana-Maria and Chen, Long and H. Computer Vision -- ECCV 2024 , pages =

    2024

  61. [61]

    Qian, Tianwen and Chen, Jingjing and Zhuo, Linhai and Jiao, Yang and Jiang, Yu-Gang , booktitle =

  62. [62]

    Computer Vision -- ECCV 2024 , pages =

    Reason2Drive: Towards Interpretable and Chain-Based Reasoning for Autonomous Driving , author =. Computer Vision -- ECCV 2024 , pages =

    2024

  63. [63]

    Sima, Chonghao and Renz, Katrin and Chitta, Kashyap and Chen, Long and Zhang, Han and Xie, Chunjing and Beisswenger, Jan and Luo, Ping and Geiger, Andreas and Li, Hongyang , booktitle =

  64. [64]

    Computer Vision -- ECCV 2024 , year =

    Dolphins: Multimodal Language Model for Driving , author =. Computer Vision -- ECCV 2024 , year =

    2024

  65. [65]

    and Velipasalar, Senem and Ren, Liu , booktitle =

    Pan, Chenbin and Yaman, Burhaneddin and Nesti, Tommaso and Mallik, Abhirup and Allievi, Alessandro G. and Velipasalar, Senem and Ren, Liu , booktitle =

  66. [66]

    Proceedings of the AAAI Conference on Artificial Intelligence , volume =

    Generative Planning with 3D-Vision Language Pre-training for End-to-End Autonomous Driving , author =. Proceedings of the AAAI Conference on Artificial Intelligence , volume =

  67. [67]

    Song, Wenxuan and Zhou, Ziyang and Zhao, Han and Chen, Jiayi and Ding, Pengxiang and Yan, Haodong and Huang, Yuxin and Tang, Feilong and Wang, Donglin and Li, Haoang , booktitle =

  68. [68]

    Proceedings of The 7th Conference on Robot Learning , series =

    Parting with Misconceptions about Learning-Based Vehicle Motion Planning , author =. Proceedings of The 7th Conference on Robot Learning , series =

  69. [69]

    2025 , eprint =

    Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models , author =. 2025 , eprint =

    2025

  70. [70]

    2025 , eprint =

    InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving , author =. 2025 , eprint =

    2025

  71. [71]

    2024 , eprint =

    Doe-1: Closed-Loop Autonomous Driving with Large World Model , author =. 2024 , eprint =

    2024

  72. [72]

    2024 , eprint =

    Making Large Language Models Better Planners with Reasoning-Decision Alignment , author =. 2024 , eprint =

    2024

  73. [73]

    Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops , pages =

    OpenEMMA: Open-Source Multimodal Model for End-to-End Autonomous Driving , author =. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops , pages =

  74. [74]

    International Conference on Learning Representations , year =

    Decoupled Weight Decay Regularization , author =. International Conference on Learning Representations , year =

  75. [75]

    2026 , eprint =

    Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation , author =. 2026 , eprint =

    2026