pith. machine review for the scientific record. sign in

arxiv: 2603.23607 · v2 · submitted 2026-03-24 · 💻 cs.CV · cs.RO

Recognition: no theorem link

LongTail Driving Scenarios with Reasoning Traces: The KITScenes LongTail Dataset

Carlos Fernandez, Christian Kinzig, Christoph Stiller, Dominik Strutz, Fabian Immel, Felix Hauser, Guillermo S. Guitierrez-Cabello, Hendrik K\"onigshof, Holger Caesar, Igor Gilitschenski, Jaime Villa, Jan-Hendrik Pauls, Kaiwen Wang, Kevin R\"osch, Marlon Steiner, Martin Lauer, Nils Alexander Rack, Omer Sahin Tas, Richard Schwarzkopf, Royden Wagner, Yinzhe Shen

Authors on Pith no claims yet

Pith reviewed 2026-05-15 00:27 UTC · model grok-4.3

classification 💻 cs.CV cs.RO
keywords long-tail drivingreasoning tracesmultimodal modelsVLMsself-driving datasetfew-shot generalizationmultilingual annotationsin-context learning
0
0 comments X

The pith

New dataset supplies detailed reasoning traces for rare driving scenarios to test multimodal models on instruction following.

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

The paper introduces the KITScenes LongTail Dataset to address the challenge of generalization to infrequent events in self-driving systems. It pairs multi-view video recordings and vehicle trajectories with high-level instructions and step-by-step reasoning traces written by domain experts. These traces appear in English, Spanish, and Chinese to reflect varied cultural perspectives on decision-making. The dataset serves as a benchmark that measures not only safety and comfort but also how well models follow instructions and produce semantically coherent outputs. A reader would care because most current driving models still fail on edge cases that occur outside common training distributions.

Core claim

The central claim is that supplying multi-view videos, trajectories, high-level instructions, and detailed multilingual reasoning traces for long-tail driving events creates a resource that supports in-context learning and few-shot generalization in vision-language models and vision-language-action models, while shifting evaluation from purely numeric safety metrics to explicit checks on instruction adherence and output coherence.

What carries the argument

The collection of detailed reasoning traces written by domain experts with diverse cultural backgrounds, attached to multi-view video and trajectory data for long-tail driving events.

If this is right

  • Multimodal models gain access to explicit reasoning examples that can be used directly for in-context learning and few-shot adaptation.
  • Evaluation expands beyond safety and comfort numbers to include measurable checks on instruction following and semantic consistency of generated outputs.
  • Researchers can compare how English, Spanish, and Chinese reasoning styles affect model behavior on the same driving scenes.
  • The dataset functions as a public benchmark for studying the role of human-like reasoning in end-to-end driving policies.

Where Pith is reading between the lines

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

  • Similar trace-augmented datasets could be built for other sequential decision domains where rare events dominate risk, such as surgical robotics or industrial automation.
  • The explicit traces open a route for human-in-the-loop debugging: failures can be traced back to specific reasoning steps rather than opaque policy outputs.
  • Integration with online adaptation loops could let deployed vehicles request and incorporate new expert traces when they encounter novel situations.

Load-bearing premise

The reasoning traces collected from domain experts accurately capture the decision processes needed for competent driving in long-tail scenarios.

What would settle it

A controlled test in which models prompted with the dataset's reasoning traces show no measurable gain in instruction-following accuracy or semantic coherence on held-out long-tail driving clips compared with models prompted only with raw video and instructions.

Figures

Figures reproduced from arXiv: 2603.23607 by Carlos Fernandez, Christian Kinzig, Christoph Stiller, Dominik Strutz, Fabian Immel, Felix Hauser, Guillermo S. Guitierrez-Cabello, Hendrik K\"onigshof, Holger Caesar, Igor Gilitschenski, Jaime Villa, Jan-Hendrik Pauls, Kaiwen Wang, Kevin R\"osch, Marlon Steiner, Martin Lauer, Nils Alexander Rack, Omer Sahin Tas, Richard Schwarzkopf, Royden Wagner, Yinzhe Shen.

Figure 1
Figure 1. Figure 1: Left: Strengths and weaknesses of datasets used to benchmark end-to-end driving: nuScenes, Waymo E2E, CoVLA, ours. Middle: A challenging long-tail scenario from our dataset. Right: The start of the expert reasoning trace for this scenario. 1 Introduction Self-driving has seen substantial progress over the past decade. Perception, once the primary bottleneck, has advanced significantly through public datase… view at source ↗
Figure 2
Figure 2. Figure 2: shows the distribution of scenario types. The distribution is approximately equal across all splits. 0 10 20 30 Specifically selected Nighttime Snow and wintry mix Heavy rain Construction zone Overtake or lane change Intersection 19.827 5.101 6.16 7.122 9.432 22.714 29.644 [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Multi-view videos with frame-wise stitching. [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Relationship between MMS and L2 vs. DrivingScore (DS), with linear fits and Pearson r values (0.59 and −0.45). 5.2 End-to-end driving evaluation: Do models generalize to our data? To cover both image-based and video-based open-source models, we evaluate Pixtral 12B [3], Gemma 3 12B [67], and Qwen3-VL 8B [7]. All open-source models are instruction-tuned [74] (i.e., trained to follow instructions by the mode… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative results. (a) to (c): We show qualitative results of turning left and right at intersections (during heavy rain) and a lane change maneuver. The blue trajectories are expert trajectories, the orange trajectories are from our wrong speed category (too low in (a) and (c), and too high in (b)), the green trajectories are from our neglect instruction category. In addition, we show the predictions of… view at source ↗
Figure 6
Figure 6. Figure 6: Front-view images of specifically selected, heavy rain, and snow scenarios. [PITH_FULL_IMAGE:figures/full_fig_p021_6.png] view at source ↗
read the original abstract

In real-world domains such as self-driving, generalization to rare scenarios remains a fundamental challenge. To address this, we introduce a new dataset designed for end-to-end driving that focuses on long-tail driving events. We provide multi-view video data, trajectories, high-level instructions, and detailed reasoning traces, facilitating in-context learning and few-shot generalization. The resulting benchmark for multimodal models, such as VLMs and VLAs, goes beyond safety and comfort metrics by evaluating instruction following and semantic coherence between model outputs. The multilingual reasoning traces in English, Spanish, and Chinese are from domain experts with diverse cultural backgrounds. Thus, our dataset is a unique resource for studying how different forms of reasoning affect driving competence. Our dataset is available at: https://hf.co/datasets/kit-mrt/kitscenes-longtail

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 the KITScenes LongTail Dataset for end-to-end driving focused on long-tail scenarios. It supplies multi-view video, trajectories, high-level instructions, and detailed multilingual reasoning traces (English, Spanish, Chinese) collected from domain experts with diverse backgrounds. The resource is presented as a benchmark for VLMs and VLAs that goes beyond safety metrics to assess instruction following and semantic coherence, with the explicit goal of supporting in-context learning and few-shot generalization.

Significance. If the reasoning traces are shown to be high-quality and effective, the dataset would fill a clear gap in long-tail driving data and enable systematic study of how different reasoning forms affect driving competence in multimodal models. The multilingual expert annotations constitute a distinctive feature that could support cross-cultural analyses of model behavior.

major comments (2)
  1. [Abstract] Abstract: the claim that the dataset 'facilitates in-context learning and few-shot generalization' is unsupported; the manuscript contains no experiments, baselines, ablations, or quantitative results demonstrating that models conditioned on these reasoning traces outperform those using generic captions or no traces on instruction-following, semantic coherence, or driving-success metrics in long-tail cases.
  2. [Dataset construction] Dataset construction section: no inter-annotator agreement scores, consistency checks, or correlation with real-world driving competence are reported for the multilingual reasoning traces, leaving the assumption that expert annotations accurately capture required decision processes unverified.
minor comments (2)
  1. Add a short table comparing the new dataset's scale, annotation richness, and scenario coverage against existing long-tail or driving datasets to clarify its incremental contribution.
  2. The dataset URL is given; ensure the release includes detailed annotation guidelines and a data card describing collection protocols and potential biases.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our dataset paper. We address each major comment below and describe the revisions we will make to the manuscript.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the dataset 'facilitates in-context learning and few-shot generalization' is unsupported; the manuscript contains no experiments, baselines, ablations, or quantitative results demonstrating that models conditioned on these reasoning traces outperform those using generic captions or no traces on instruction-following, semantic coherence, or driving-success metrics in long-tail cases.

    Authors: We agree that the manuscript provides no empirical results or baselines demonstrating that the reasoning traces improve in-context learning or few-shot generalization. As this is a dataset introduction paper, the original phrasing was intended to describe intended use cases rather than demonstrated outcomes. We will revise the abstract to state that the dataset is designed to support studies of in-context learning and few-shot generalization in long-tail driving scenarios, removing any implication of verified performance gains. revision: yes

  2. Referee: [Dataset construction] Dataset construction section: no inter-annotator agreement scores, consistency checks, or correlation with real-world driving competence are reported for the multilingual reasoning traces, leaving the assumption that expert annotations accurately capture required decision processes unverified.

    Authors: We acknowledge that the current manuscript does not report inter-annotator agreement scores, formal consistency metrics, or correlations between the traces and real-world driving outcomes. The traces were produced by domain experts following a structured protocol, but no quantitative agreement analysis was performed. In revision we will expand the dataset construction section with a detailed description of the annotation guidelines, any qualitative quality controls applied, and an explicit discussion of this limitation, including plans for future verification studies. revision: partial

Circularity Check

0 steps flagged

Dataset release paper contains no derivation chain or self-referential predictions

full rationale

This is a data resource paper introducing the KITScenes LongTail Dataset with multi-view videos, trajectories, instructions, and multilingual reasoning traces. No equations, fitted parameters, predictions, or derivations appear in the abstract or described content. Claims about facilitating in-context learning and few-shot generalization are stated as intended uses of the released data rather than results derived from any internal model or computation. No self-citations, uniqueness theorems, or ansatzes are invoked to support any load-bearing step. The work is self-contained as a benchmark release with no circular reduction of outputs to inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical model, free parameters, or invented entities; the contribution is empirical data collection.

pith-pipeline@v0.9.0 · 5522 in / 895 out tokens · 23925 ms · 2026-05-15T00:27:43.406563+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

89 extracted references · 23 canonical work pages · 11 internal anchors

  1. [1]

    OpenAI o1 System Card

    (2024), O.: OpenAI o1 System Card. arXiv preprint arXiv:2412.16720 (2024) 3, 11

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  2. [2]

    Cosmos World Foundation Model Platform for Physical AI

    Agarwal, N., Ali, A., Bala, M., Balaji, Y., Barker, E., Cai, T., Chattopadhyay, P., Chen, Y., Cui, Y., Ding, Y., et al.: Cosmos World Foundation Model Platform for Physical AI. arXiv preprint arXiv:2501.03575 (2025) 2, 7

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  3. [3]

    Pixtral 12B

    Agrawal, P., Antoniak, S., Hanna, E.B., Bout, B., Chaplot, D., Chudnovsky, J., Costa, D., De Monicault, B., Garg, S., Gervet, T., et al.: Pixtral 12B. arXiv preprint arXiv:2410.07073 (2024) 9, 10, 11, 16

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  4. [4]

    AI, P.: Perplexity Pro (2025),https://www.perplexity.ai/pro, aI-powered research assistant and conversational search engine 9, 18

    2025

  5. [5]

    In: NeurIPS (2022) 3

    Alayrac, J.B., Donahue, J., Luc, P., Miech, A., Barr, I., Hasson, Y., Lenc, K., Mensch, A., Millican, K., Reynolds, M., et al.: Flamingo: a Visual Language Model for Few-Shot Learning. In: NeurIPS (2022) 3

    2022

  6. [6]

    In: WACV (2025) 3, 4

    Arai, H., Miwa, K., Sasaki, K., Watanabe, K., Yamaguchi, Y., Aoki, S., Yamamoto, I.: CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving. In: WACV (2025) 3, 4

    2025

  7. [7]

    Qwen3-VL Technical Report

    Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et al.: Qwen3-vl technical report. arXiv preprint arXiv:2511.21631 (2025) 9, 10, 11, 16

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  8. [8]

    In: NeurIPS (2020) 2

    Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.: Language Models are Few-Shot Learners. In: NeurIPS (2020) 2

    2020

  9. [9]

    In: CVPR (2020) 1, 2, 3, 4

    Caesar, H., Bankiti, V., et al.: nuScenes: A Multimodal Dataset for Autonomous Driving. In: CVPR (2020) 1, 2, 3, 4

    2020

  10. [10]

    arXiv preprint arXiv:2106.11810 (2021) 3, 7

    Caesar, H., Kabzan, J., Tan, K.S., Fong, W.K., Wolff, E., Lang, A., Fletcher, L., Beijbom, O., Omari, S.: nuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles. arXiv preprint arXiv:2106.11810 (2021) 3, 7

    work page arXiv 2021

  11. [11]

    arXiv preprint arXiv:2509.25413 (2025) 9

    Cai, Z., Yeh, C.F., Xu, H., Liu, Z., Meyer, G., Lei, X., Zhao, C., Li, S.W., Chandra, V., Shi, Y.: DepthLM: Metric Depth From Vision Language Models. arXiv preprint arXiv:2509.25413 (2025) 9

    work page arXiv 2025

  12. [12]

    In: CoRL (2025) 2

    Cao, W., Hallgarten, M., Li, T., Dauner, D., Gu, X., Wang, C., Miron, Y., Aiello, M., Li, H., Gilitschenski, I., et al.: Pseudo-Simulation for Autonomous Driving. In: CoRL (2025) 2

    2025

  13. [13]

    In: ICCV (2025) 3

    Chang, W.J., Zhan, W., Tomizuka, M., Chandraker, M., Pittaluga, F.: LANGTRAJ: Diffusion Model and Dataset for Language-Conditioned Trajectory Simulation. In: ICCV (2025) 3

    2025

  14. [14]

    arXiv preprint arXiv:2512.10942 (2025) 11

    Chen, D., Shukor, M., Moutakanni, T., Chung, W., Yu, J., Kasarla, T., Bolourchi, A., LeCun, Y., Fung, P.: Vl-jepa: Joint embedding predictive architecture for vision-language. arXiv preprint arXiv:2512.10942 (2025) 11

    work page arXiv 2025

  15. [15]

    In: NeurIPS (2024) 2, 3, 7

    Dauner, D., Hallgarten, M., Li, T., Weng, X., Huang, Z., Yang, Z., Li, H., Gilitschenski, I., Ivanovic, B., Pavone, M., et al.: NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking. In: NeurIPS (2024) 2, 3, 7

    2024

  16. [16]

    In: CVPR (2025) 3, 6

    Deitke, M., Clark, C., Lee, S., Tripathi, R., Yang, Y., Park, J.S., Salehi, M., Muennighoff, N., Lo, K., Soldaini, L., et al.: Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models. In: CVPR (2025) 3, 6

    2025

  17. [17]

    In: ICLR (2021) 4

    Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: ICLR (2021) 4

    2021

  18. [18]

    In: CoRL (2017) 3

    Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: An Open Urban Driving Simulator. In: CoRL (2017) 3

    2017

  19. [19]

    PaLM-E: An Embodied Multimodal Language Model

    Driess, D., Xia, F., Sajjadi, M.S.M., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., Huang, W., Chebotar, Y., Sermanet, P., Duckworth, D., Levine, S., Vanhoucke, V., Hausman, K., Toussaint, M., Greff, K., Zeng, A., Mordatch, I., Florence, P.: PaLM-E: An Embodied Multimodal Language Model. In: arXiv preprint arXiv:2303.033...

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  20. [20]

    In: ICCV (2021) 8 LongTail Driving Scenarios 13

    Ettinger, S., Cheng, S., Caine, B., Liu, C., Zhao, H., Pradhan, S., Chai, Y., Sapp, B., Qi, C.R., Zhou, Y., et al.: Large Scale Interactive Motion Forecasting for Autonomous Driving: The Waymo Open Motion Dataset. In: ICCV (2021) 8 LongTail Driving Scenarios 13

    2021

  21. [21]

    In: NeurIPS (2024) 2

    Fent, F., Kuttenreich, F., Ruch, F., Rizwin, F., Juergens, S., Lechermann, L., Nissler, C., Perl, A., Voll, U., Yan, M., Lienkamp, M.: MAN TruckScenes: A Multimodal Dataset for Autonomous Trucking in Diverse Conditions. In: NeurIPS (2024) 2

    2024

  22. [22]

    In: NeurIPS (2024) 7

    Gao, S., Yang, J., Chen, L., Chitta, K., Qiu, Y., Geiger, A., Zhang, J., Li, H.: Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability. In: NeurIPS (2024) 7

    2024

  23. [23]

    The International Journal of Robotics Research32(11), 1231–1237 (2013).https://doi.org/10.1177/0278364913491297,https: //journals.sagepub.com/doi/10.1177/02783649134912972

    Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets Robotics: The KITTI Dataset. The International Journal of Robotics Research32(11), 1231–1237 (2013).https://doi.org/10.1177/0278364913491297,https: //journals.sagepub.com/doi/10.1177/02783649134912972

    work page doi:10.1177/0278364913491297 2013

  24. [24]

    In: CVPR (2012) 1, 2

    Geiger, A., Lenz, P., Urtasun, R.: Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In: CVPR (2012) 1, 2

    2012

  25. [25]

    How Long Does It Take to Stop?

    Green, M.: "How Long Does It Take to Stop?" Methodological Analysis of Driver Perception-Brake Times. Transportation Human Factors2(3), 195–216 (2000) 7

    2000

  26. [26]

    129483, 11

    Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., Bi, X., et al.: DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (2025),https://arxiv.org/abs/2501. 129483, 11

    2025

  27. [27]

    In: NeurIPS (2021) 10

    Hendrycks, D., Burns, C., Kadavath, S., Arora, A., Basart, S., Tang, E., Song, D., Steinhardt, J.: Measuring Mathematical Problem Solving With the MATH Dataset. In: NeurIPS (2021) 10

    2021

  28. [28]

    In: CVPR (2023) 2, 9, 10, 16

    Hu, Y., Yang, J., Chen, L., Li, K., Sima, C., Zhu, X., Chai, S., Du, S., Lin, T., Wang, W., et al.: Planning-oriented Autonomous Driving. In: CVPR (2023) 2, 9, 10, 16

    2023

  29. [29]

    ACM Transactions on Information Systems43(2), 1–55 (2025) 10

    Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., Qin, B., et al.: A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions. ACM Transactions on Information Systems43(2), 1–55 (2025) 10

    2025

  30. [30]

    Transactions on Machine Learning Research (2025) 2, 8, 9

    Hwang, J.J., Xu, R., Lin, H., Hung, W.C., Ji, J., Choi, K., Huang, D., He, T., Covington, P., Sapp, B., Zhou, Y., Guo, J., Anguelov, D., Tan, M.: EMMA: End-to-end multimodal model for autonomous driving. Transactions on Machine Learning Research (2025) 2, 8, 9

    2025

  31. [31]

    In: CoRL (2025) 3

    Intelligence, P., Black, K., Brown, N., Darpinian, J., Dhabalia, K., Driess, D., Esmail, A., Equi, M., Finn, C., Fusai, N., et al.:π0.5: a Vision-Language-Action Model with Open-World Generalization. In: CoRL (2025) 3

    2025

  32. [32]

    LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

    Jain, N., Han, K., Gu, A., Li, W.D., Yan, F., Zhang, T., Wang, S., Solar-Lezama, A., Sen, K., Stoica, I.: Live- CodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code. arXiv preprint arXiv:2403.07974 (2024) 10

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  33. [33]

    In: NeurIPS (2024) 3, 5, 7, 8

    Jia, X., Yang, Z., Li, Q., Zhang, Z., Yan, J.: Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving. In: NeurIPS (2024) 3, 5, 7, 8

    2024

  34. [34]

    In: ICCV (2023) 2

    Jiang, B., Chen, S., Xu, Q., Liao, B., Chen, J., Zhou, H., Zhang, Q., Liu, W., Huang, C., Wang, X.: VAD: Vectorized Scene Representation for Efficient Autonomous Driving. In: ICCV (2023) 2

    2023

  35. [35]

    Karan, A., Du, Y.: Reasoning with Sampling: Your Base Model is Smarter Than You Think (2025),https: //arxiv.org/abs/2510.149013

    work page arXiv 2025

  36. [36]

    TMLR (2025) 1

    Ke, Z., Jiao, F., Ming, Y., Nguyen, X.P., Xu, A., Long, D.X., Li, M., Qin, C., Wang, P., silvio savarese, Xiong, C., Joty, S.: A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems. TMLR (2025) 1

    2025

  37. [37]

    In: 2022 25th International Conference on Information Fusion (FUSION)

    Kinzig, C., Cortés, I., Fernández, C., Lauer, M.: Real-time seamless image stitching in autonomous driving. In: 2022 25th International Conference on Information Fusion (FUSION). pp. 1–8. IEEE (2022) 5

    2022

  38. [38]

    In: Forum Bildverarbeitung 2024

    Kinzig, C., Yifan, J., Lauer, M., Stiller, C.: Image stitching using gradual image warping in autonomous driving. In: Forum Bildverarbeitung 2024. p. 221. KIT Scientific Publishing (2024) 5

    2024

  39. [39]

    In: IEEE Intelligent Vehicles Symposium (IV) (2015) 11

    Kong, J., Pfeiffer, M., Schildbach, G., Borrelli, F.: Kinematic and dynamic vehicle models for autonomous driving control design. In: IEEE Intelligent Vehicles Symposium (IV) (2015) 11

    2015

  40. [40]

    Measuring Faithfulness in Chain-of-Thought Reasoning

    Lanham, T., Chen, A., Radhakrishnan, A., Steiner, B., Denison, C., Hernandez, D., Li, D., Durmus, E., Hubinger, E., Kernion, J., et al.: Measuring Faithfulness in Chain-of-Thought Reasoning. arXiv preprint arXiv:2307.13702 (2023) 7

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  41. [41]

    In: ICCV (2025) 3

    Li, D., Zhang, Y., Cao, M., Liu, D., Xie, W., Hui, T., Lin, L., Xie, Z., Li, Y.: Towards Long-Horizon Vision- Language-Action System: Reasoning, Acting and Memory. In: ICCV (2025) 3

    2025

  42. [42]

    In: ICML (2022) 3

    Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In: ICML (2022) 3

    2022

  43. [43]

    arXiv preprint arXiv:2506.02265 (2025) 9

    Li, S., Kachana, P., Chidananda, P., Nair, S., Furukawa, Y., Brown, M.: Rig3R: Rig-Aware Conditioning for Learned 3D Reconstruction. arXiv preprint arXiv:2506.02265 (2025) 9

    work page arXiv 2025

  44. [44]

    arXiv preprint arXiv:2509.19249 (2025) 7

    Li, S., Li, K., Xu, Z., Huang, G., Yang, E., Li, K., Wu, H., Wu, J., Zheng, Z., Zhang, C., et al.: Reinforcement Learning on Pre-Training Data. arXiv preprint arXiv:2509.19249 (2025) 7

    work page arXiv 2025

  45. [45]

    In: ICML (2025) 3

    Li, Y., Fan, C., Ge, C., Zhao, Z., Li, C., Xu, C., Yao, H., Tomizuka, M., Zhou, B., Tang, C., et al.: WOMD- Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving. In: ICML (2025) 3

    2025

  46. [46]

    Li, Z., Yu, Z., Lan, S., Li, J., Kautz, J., Lu, T., Alvarez, J.M.: Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving? In: CVPR (2024) 2 14 Wagner et al

    2024

  47. [47]

    Pattern Analysis and Machine Intelligence (PAMI) (2022) 2

    Liao, Y., Xie, J., Geiger, A.: KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D. Pattern Analysis and Machine Intelligence (PAMI) (2022) 2

    2022

  48. [48]

    In: NeurIPS (2023) 3

    Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual Instruction Tuning. In: NeurIPS (2023) 3

    2023

  49. [49]

    In: NeurIPS (2024) 3

    Liu, J., Liu, M., Wang, Z., An, P., Li, X., Zhou, K., Yang, S., Zhang, R., Guo, Y., Zhang, S.: RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation. In: NeurIPS (2024) 3

    2024

  50. [50]

    In: ECCV (2024) 2, 7

    Ljungbergh, W., Tonderski, A., Johnander, J., Caesar, H., Åström, K., Felsberg, M., Petersson, C.: Neuroncap: Photorealistic closed-loop safety testing for autonomous driving. In: ECCV (2024) 2, 7

    2024

  51. [51]

    In: NeurIPS (2024) 1

    Madan, A., Peri, N., Kong, S., Ramanan, D.: Revisiting Few-Shot Object Detection with Vision-Language Models. In: NeurIPS (2024) 1

    2024

  52. [52]

    Cambridge University Press (2008),http://nlp.stanford.edu/IR-book/html/htmledition/rocchio-classification-1.html6

    Manning, C.D., Raghavan, P., Schütze, H.: Introduction to Information Retrieval. Cambridge University Press (2008),http://nlp.stanford.edu/IR-book/html/htmledition/rocchio-classification-1.html6

    2008

  53. [53]

    In: NeurIPS (2025) 2, 7

    Mousakhan, A., Mittal, S., Galesso, S., Farid, K., Brox, T.: Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models. In: NeurIPS (2025) 2, 7

    2025

  54. [54]

    In: NeurIPS (2023) 3

    Mu, Y., Zhang, Q., Hu, M., Wang, W., Ding, M., Jin, J., Wang, B., Dai, J., Qiao, Y., Luo, P.: EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought. In: NeurIPS (2023) 3

    2023

  55. [55]

    In: EACL (2023) 6

    Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: Massive Text Embedding Benchmark. In: EACL (2023) 6

    2023

  56. [56]

    In: ICML (2023) 6

    Radford, A., Kim, J., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust Speech Recognition via Large- Scale Weak Supervision. In: ICML (2023) 6

    2023

  57. [57]

    In: CVPR (2025) 8

    Renz, K., Chen, L., Arani, E., Sinavski, O.: Simlingo: Vision-only closed-loop autonomous driving with language- action alignment. In: CVPR (2025) 8

    2025

  58. [58]

    arXiv preprint arXiv:2506.11234 (2025) 2, 8, 10

    Rowe, L., de Schaetzen, R., Girgis, R., Pal, C., Paull, L.: Poutine: Vision-Language-Trajectory Pre-Training and Reinforcement Learning Post-Training Enable Robust End-to-End Autonomous Driving. arXiv preprint arXiv:2506.11234 (2025) 2, 8, 10

    work page arXiv 2025

  59. [59]

    TMLR (2025) 9, 10, 16

    Shen, Y., Tas, O.S., Wang, K., Wagner, R., Stiller, C.: Divide and Merge: Motion and Semantic Learning in End-to-End Autonomous Driving. TMLR (2025) 9, 10, 16

    2025

  60. [60]

    Nature631(8022), 755–759 (2024) 4

    Shumailov, I., Shumaylov, Z., Zhao, Y., Papernot, N., Anderson, R., Gal, Y.: Ai models collapse when trained on recursively generated data. Nature631(8022), 755–759 (2024) 4

    2024

  61. [61]

    In: ECCV (2024) 2, 3, 10

    Sima, C., Renz, K., Chitta, K., Chen, L., Zhang, H., Xie, C., Beißwenger, J., Luo, P., Geiger, A., Li, H.: DriveLM: Driving with Graph Visual Question Answering. In: ECCV (2024) 2, 3, 10

    2024

  62. [62]

    OpenAI GPT-5 System Card

    Singh, A., Fry, A., Perelman, A., Tart, A., Ganesh, A., El-Kishky, A., McLaughlin, A., Low, A., Ostrow, A., Ananthram, A., et al.: OpenAI GPT-5 System Card. arXiv preprint arXiv:2601.03267 (2025) 9, 10, 16

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  63. [63]

    In: CVPR (2020) 1, 2

    Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et al.: Scalability in Perception for Autonomous Driving. In: CVPR (2020) 1, 2

    2020

  64. [64]

    In: ICRA (2025) 2

    Sun, W., Lin, X., Shi, Y., Zhang, C., Wu, H., Zheng, S.: SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation. In: ICRA (2025) 2

    2025

  65. [65]

    In: ICLR (2025) 6

    Tas, O.S., Wagner, R.: Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers. In: ICLR (2025) 6

    2025

  66. [66]

    arXiv (2025) 9, 10, 16

    Team, G.R.: Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer. arXiv (2025) 9, 10, 16

    2025

  67. [67]

    Gemma 3 Technical Report

    Team, G., Kamath, A., Ferret, J., Pathak, S., Vieillard, N., Merhej, R., Perrin, S., Matejovicova, T., Ramé, A., Rivière, M., et al.: Gemma 3 Technical Report. arXiv preprint arXiv:2503.19786 (2025) 9, 10, 11, 16

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  68. [68]

    arXiv preprint arXiv:2509.20354 (2025) 6

    Vera, H.S., Dua, S., Zhang, B., Salz, D., Mullins, R., Panyam, S.R., Smoot, S., Naim, I., Zou, J., Chen, F., et al.: EmbeddingGemma: Powerful and Lightweight Text Representations. arXiv preprint arXiv:2509.20354 (2025) 6

    work page arXiv 2025

  69. [69]

    In: CVPR (2025) 3

    Wang, S., Yu, Z., Jiang, X., Lan, S., Shi, M., Chang, N., Kautz, J., Li, Y., Alvarez, J.M.: OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning. In: CVPR (2025) 3

    2025

  70. [70]

    Wang, X., Alabdulmohsin, I., Salz, D., Li, Z., Rong, K., Zhai, X.: Scaling Pre-training to One Hundred Billion Data for Vision Language Models (2025),https://arxiv.org/abs/2502.0761711

    work page arXiv 2025

  71. [71]

    In: ICLR (2023) 3

    Wang, X., Wei, J., Schuurmans, D., Le, Q., Chi, E., Narang, S., Chowdhery, A., Zhou, D.: Self-Consistency Improves Chain of Thought Reasoning in Language Models. In: ICLR (2023) 3

    2023

  72. [72]

    In: ICCV (2025) 3

    Wang, Y., Zhu, H., Liu, M., Yang, J., Fang, H.S., He, T.: VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers. In: ICCV (2025) 3

    2025

  73. [73]

    Waymo Open Dataset: Vision-based End-to-End Driving Challenge 2025.https://waymo.com/open/challenges/ 2025/e2e-driving(2025), accessed: 2025-11-01 3, 5, 7

    2025

  74. [74]

    In: ICLR (2022) 9

    Wei, J., Bosma, M., Zhao, V., Guu, K., Yu, A.W., Lester, B., Du, N., Dai, A.M., Le, Q.V.: Finetuned Language Models are Zero-Shot Learners. In: ICLR (2022) 9

    2022

  75. [75]

    In: NeurIPS (2022) 2, 3, 9 LongTail Driving Scenarios 15

    Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V., Zhou, D., et al.: Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In: NeurIPS (2022) 2, 3, 9 LongTail Driving Scenarios 15

    2022

  76. [76]

    Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

    Wilson, B., Qi, W., Agarwal, T., Lambert, J., Singh, J., Khandelwal, S., Pan, B., Kumar, R., Hartnett, A., Pontes, J.K., et al.: Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting. arXiv:2301.00493 (2023) 2

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  77. [77]

    arXiv preprint arXiv:2510.26909 (2025) 8

    Windecker, T., Patel, M., Reuss, M., Schwarzkopf, R., Cadena, C., Lioutikov, R., Hutter, M., Frey, J.: NaviTrace: Evaluating Embodied Navigation of Vision-Language Models. arXiv preprint arXiv:2510.26909 (2025) 8

    work page arXiv 2025

  78. [78]

    In: NeurIPS (2025) 1

    Xia, Z., Li, J., Lin, Z., Wang, X., Wang, Y., Yang, M.H.: OpenAD: Open-world autonomous driving benchmark for 3d object detection. In: NeurIPS (2025) 1

    2025

  79. [79]

    LLMs Can Get "Brain Rot": A Pilot Study on Twitter/X

    Xing, S., Hong, J., Wang, Y., Chen, R., Zhang, Z., Grama, A., Tu, Z., Wang, Z.: LLMs Can Get" Brain Rot"! arXiv preprint arXiv:2510.13928 (2025) 4

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  80. [80]

    In: EMPL (2024) 10

    Xu, R., Qi, Z., Guo, Z., Wang, C., Wang, H., Zhang, Y., Xu, W.: Knowledge Conflicts for LLMs: A Survey. In: EMPL (2024) 10

    2024

Showing first 80 references.