Pith. sign in

REVIEW 1 major objections 1 minor 38 references

A benchmark of 4,331 instances shows vision-language models remain far below human performance on spatial tasks for low-altitude UAVs.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-01 06:48 UTC pith:KZVSRESM

load-bearing objection SpatialUAV releases a new benchmark covering multi-view UAV collaboration and motion tasks that prior datasets skipped, with model evaluations showing clear gaps. the 1 major comments →

arxiv 2606.27876 v2 pith:KZVSRESM submitted 2026-06-26 cs.CV cs.AI

SpatialUAV: Benchmarking Spatial Intelligence for Low-Altitude UAV Perception, Collaboration, and Motion

Haoyu Zhang , Meng Liu , Qianlong Xiang , Kun Wang , Yaowei Wang , Liqiang Nie This is my paper
classification cs.CV cs.AI
keywords UAV perceptionspatial intelligencebenchmarkvision-language modelslow-altitude UAVmulti-view collaborationgeometric reasoningmotion understanding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

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

The paper introduces SpatialUAV to measure spatial intelligence required for low-altitude UAV perception, collaboration, and navigation. It organizes 4,331 instances into 14 task types that test semantic discrimination, spatial relations, aerial-aerial and aerial-ground collaboration, and motion understanding under seven input setups and nine answer formats. Systematic evaluation of representative vision-language models reveals clear shortfalls relative to human performance, concentrated in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding. The benchmark supplies standardized tasks and metrics intended to direct future model development toward the spatial demands of real UAV operations.

Core claim

The paper establishes SpatialUAV, a real low-altitude UAV benchmark with 4,331 curated instances across 14 fine-grained task types supporting multiple input configurations and answer formats. Through systematic evaluation, it finds that current vision-language models are far from human-level performance with clear weaknesses in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding.

What carries the argument

The SpatialUAV benchmark with its unified visual-input-question-answer schema, supported by a construction pipeline that uses detector-assisted regions, depth supervision, metadata rules, and multi-turn human validation to produce reliable heterogeneous outputs.

Load-bearing premise

The 14 task formulations and 4,331 instances accurately capture the spatial intelligence needed for real low-altitude UAV perception and collaboration without selection bias or annotation artifacts.

What would settle it

A controlled evaluation in which any vision-language model reaches or exceeds human-level scores across all 14 tasks on the SpatialUAV benchmark would falsify the reported performance gaps.

Watch this falsifier — get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

1 major / 1 minor

Summary. The paper introduces SpatialUAV, a real low-altitude UAV benchmark with 4,331 curated instances across 14 task types covering semantic discrimination, spatial relations, aerial-aerial and aerial-ground collaboration, and motion understanding. It uses a unified visual-input-question-answer schema supporting seven input configurations and nine answer formats, constructed via detector-assisted regions, depth supervision, metadata rules, manual annotation, blind filtering, and multi-turn human validation. Evaluations of representative vision-language models show they remain far from human-level performance, with bottlenecks in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding.

Significance. If the benchmark construction is robust, the work supplies a valuable, publicly released resource that exposes concrete gaps in current models for UAV spatial tasks and supplies empirical guidance for future model development in low-altitude perception and collaboration.

major comments (1)
  1. [Data Construction Pipeline] Data Construction Pipeline (abstract and §3): the pipeline is described at high level (detector-assisted regions, depth supervision, blind filtering, multi-turn validation). To substantiate that the 4,331 instances faithfully measure the intended spatial intelligence without selection bias or annotation artifacts, the manuscript must supply quantitative inter-annotator agreement statistics, explicit exclusion criteria, and precise definitions of the task-specific metrics used for the nine heterogeneous answer formats.
minor comments (1)
  1. [Abstract] Abstract: the phrase 'extensive manual annotation' is used without indicating the number of annotators or the exact validation protocol; this detail belongs in the main text even if summarized in the abstract.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive evaluation and recommendation of minor revision. The single major comment concerns the level of detail in the data construction pipeline; we address it directly below and will incorporate the requested information in the revised manuscript.

read point-by-point responses

  1. Referee: [Data Construction Pipeline] Data Construction Pipeline (abstract and §3): the pipeline is described at high level (detector-assisted regions, depth supervision, blind filtering, multi-turn validation). To substantiate that the 4,331 instances faithfully measure the intended spatial intelligence without selection bias or annotation artifacts, the manuscript must supply quantitative inter-annotator agreement statistics, explicit exclusion criteria, and precise definitions of the task-specific metrics used for the nine heterogeneous answer formats.

    Authors: We agree that the current description in §3 is high-level and that quantitative evidence of annotation quality would strengthen the claim that the benchmark faithfully measures spatial intelligence. In the revision we will expand §3 with: (1) inter-annotator agreement statistics (Cohen’s κ and raw agreement percentages) computed on the multi-turn human validation subset; (2) the explicit exclusion criteria applied during blind filtering (e.g., minimum region size, depth consistency thresholds, and semantic ambiguity rules); and (3) precise, task-by-task definitions of the nine answer-format metrics, including how region-identifier, geometric-value, cross-view correspondence, and free-form motion-description outputs are scored. These additions will be accompanied by a short table summarizing the statistics and criteria. revision: yes

Circularity Check

0 steps flagged

No significant circularity; empirical benchmark with no derivations or fitted predictions

full rationale

The paper introduces SpatialUAV as a benchmark dataset and evaluates existing models on it. No equations, first-principles derivations, parameter fitting, or 'predictions' appear in the abstract or described pipeline. Construction uses detector-assisted regions, depth supervision, metadata rules, manual annotation, blind filtering, and multi-turn validation, but these are procedural safeguards rather than self-referential definitions or fitted inputs renamed as outputs. No self-citation chains, uniqueness theorems, or ansatzes are invoked. The central claim (models lag human performance on spatial tasks) rests on external model evaluations against the released data, not on any internal reduction. This matches the expected non-finding for benchmark releases.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

Benchmark construction assumes human annotations and detector outputs provide ground truth without systematic bias; no free parameters or invented entities are introduced.

axioms (2)
  • domain assumption Human annotators following the described multi-turn validation protocol produce consistent and accurate labels for spatial relations and motion descriptions.
    Invoked in the data construction pipeline paragraph of the abstract.
  • domain assumption The selected 14 task types and input configurations collectively capture the spatial intelligence requirements of low-altitude UAV perception and collaboration.
    Stated as motivation for addressing gaps in existing benchmarks.

pith-pipeline@v0.9.1-grok · 5805 in / 1325 out tokens · 26280 ms · 2026-07-01T06:48:25.071775+00:00 · methodology

0 comments
read the original abstract

Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation. However, existing UAV benchmarks often emphasize image-level recognition, single-view understanding, or narrow answer formats, leaving 3D spatial inference, multi-view collaboration, scene dynamics, and diverse task formulations insufficiently evaluated. To address these gaps, we introduce SpatialUAV, a real low-altitude UAV benchmark comprising 4,331 curated instances across 14 fine-grained task types, covering semantic discrimination, spatial relation, aerial--aerial collaboration, aerial--ground collaboration, and motion understanding. SpatialUAV organizes all samples into a unified visual-input--question--answer schema, while supporting seven input configurations and nine answer formats, including option labels, region identifiers, geometric values, cross-view correspondences, and free-form motion descriptions. To ensure reliable and grounded evaluation, our data construction pipeline integrates detector-assisted regions, depth supervision, metadata-derived rules, extensive manual annotation, blind filtering, and multi-turn human validation, together with task-specific metrics for heterogeneous outputs. Evaluating representative vision-language models across three categories, we show that current models remain far from human-level performance, with pronounced bottlenecks in cross-view association, structured grounding, geometric reasoning, and temporal viewpoint understanding. These results offer empirical guidance for advancing low-altitude UAV spatial intelligence. Code and data are available at https://github.com/Hyu-Zhang/SpatialUAV.

Figures

Figures reproduced from arXiv: 2606.27876 by Haoyu Zhang, Kun Wang, Liqiang Nie, Meng Liu, Qianlong Xiang, Yaowei Wang.

Figure 1
Figure 1. Figure 1: Representative examples from SpatialUAV. Colored panels denote different evaluation settings: [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overall construction pipeline of SpatialUAV. In the task synthesis step, each instance is constructed by organizing task-specific visual inputs, designing [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 4
Figure 4. Figure 4: Answer-format distribution of SpatialUAV. The histogram reports the [PITH_FULL_IMAGE:figures/full_fig_p004_4.png] view at source ↗
Figure 3
Figure 3. Figure 3: Task distribution of SpatialUAV. The inner ring shows the major [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Answer-format distribution of SpatialUAV. The histogram reports the [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Macro-average performance across SpatialUAV reasoning groups. [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Qualitative cases on representative SpatialUAV tasks. The examples cover aerial–aerial camera transformation, aerial–aerial object matching, and [PITH_FULL_IMAGE:figures/full_fig_p008_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Answer-format ablation across four representative tasks. Each panel reports one model, with Orig. and MC denoting the original structured-answer [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗

Review history (2 revisions) →

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

38 extracted references · 14 canonical work pages · 4 internal anchors

  1. [1]

    Long-short match for lost control in uav multi-object tracking,

    Z. Zou, M. Ye, L. Ji, L. Zhou, S. Tang, Y . Gan, and S. Li, “Long-short match for lost control in uav multi-object tracking,”IEEE Transactions on Multimedia, vol. 28, pp. 786–800, 2026

    2026

  2. [2]

    Fre-stformer: A frequency-based spatio-temporal transformer for uav human action recognition,

    T. Xiang, X. Xia, J. Yuan, and Z. Tu, “Fre-stformer: A frequency-based spatio-temporal transformer for uav human action recognition,”IEEE Transactions on Multimedia, pp. 1–13, 2026

    2026

  3. [3]

    Mode-track: Robust multi-object tracking with motion decoupling in uav videos,

    Z. Song, Y . Li, S. Zhou, W. Tang, and L. Wang, “Mode-track: Robust multi-object tracking with motion decoupling in uav videos,”IEEE Transactions on Multimedia, pp. 1–11, 2026

    2026

  4. [4]

    A survey of robotic language grounding: tradeoffs between symbols and embeddings,

    V . Cohen, J. X. Liu, R. Mooney, S. Tellex, and D. Watkins, “A survey of robotic language grounding: tradeoffs between symbols and embeddings,” inProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024, pp. 7999–8009

    2024

  5. [5]

    Embodiedscan: A holistic multi-modal 3d perception suite towards embodied ai,

    T. Wang, X. Mao, C. Zhu, R. Xu, R. Lyu, P. Li, X. Chen, W. Zhang, K. Chen, T. Xueet al., “Embodiedscan: A holistic multi-modal 3d perception suite towards embodied ai,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 19 757–19 767

    2024

  6. [6]

    Egothink: Evaluating first-person perspective thinking capability of vision-language models,

    S. Cheng, Z. Guo, J. Wu, K. Fang, P. Li, H. Liu, and Y . Liu, “Egothink: Evaluating first-person perspective thinking capability of vision-language models,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14 291–14 302

    2024

  7. [7]

    Spatialvlm: Endowing vision-language models with spatial reasoning capabilities,

    B. Chen, Z. Xu, S. Kirmani, B. Ichter, D. Sadigh, L. Guibas, and F. Xia, “Spatialvlm: Endowing vision-language models with spatial reasoning capabilities,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14 455–14 465

    2024

  8. [8]

    Thinking in space: How multimodal large language models see, remember, and recall spaces,

    J. Yang, S. Yang, A. W. Gupta, R. Han, L. Fei-Fei, and S. Xie, “Thinking in space: How multimodal large language models see, remember, and recall spaces,” inProceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 10 632–10 643

    2025

  9. [9]

    Urbanvideo-bench: Benchmarking vision-language models on embodied intelligence with video data in urban spaces,

    B. Zhao, J. Fang, Z. Dai, Z. Wang, J. Zha, W. Zhang, C. Gao, Y . Wang, J. Cui, X. Chenet al., “Urbanvideo-bench: Benchmarking vision-language models on embodied intelligence with video data in urban spaces,” inProceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pp. 32 400– 32 423

    2025

  10. [10]

    Cityeqa: A hierarchical llm agent on embodied question answering benchmark in city space,

    Y . Zhao, K. Xu, Z. Zhu, Y . Hu, Z. Zheng, Y . Chen, Y . Ji, C. Gao, Y . Li, and J. Huang, “Cityeqa: A hierarchical llm agent on embodied question answering benchmark in city space,” inProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025, pp. 12 465–12 480

    2025

  11. [11]

    Anti-uav: A large-scale benchmark for vision-based uav tracking,

    N. Jiang, K. Wang, X. Peng, X. Yu, Q. Wang, J. Xing, G. Li, G. Guo, Q. Ye, J. Jiao, J. Zhao, and Z. Han, “Anti-uav: A large-scale benchmark for vision-based uav tracking,”IEEE Transactions on Multimedia, vol. 25, pp. 486–500, 2023

    2023

  12. [12]

    Open3d-vqa: A benchmark for embodied spatial concept reasoning with multimodal large language model in open space,

    W. Zhang, Z. Zhou, X. Zeng, L. Xuchen, J. Fang, C. Gao, J. Cui, Y . Li, X. Chen, and X.-P. Zhang, “Open3d-vqa: A benchmark for embodied spatial concept reasoning with multimodal large language model in open space,” inProceedings of the 33rd ACM International Conference on Multimedia, 2025, pp. 12 784–12 791

    2025

  13. [13]

    Is your vlm sky-ready? a comprehensive spatial intelligence benchmark for uav navigation.arXiv preprint arXiv:2511.13269, 2025

    L. Zhang, Y . Zhang, H. Li, H. Fu, Y . Tang, H. Ye, L. Chen, X. Liang, X. Hao, and W. Ding, “Is your vlm sky-ready? a comprehensive spatial intelligence benchmark for uav navigation,”arXiv preprint arXiv:2511.13269, 2025

    work page arXiv 2025

  14. [14]

    Scanqa: 3d question answering for spatial scene understanding,

    D. Azuma, T. Miyanishi, S. Kurita, and M. Kawanabe, “Scanqa: 3d question answering for spatial scene understanding,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19 129–19 139

    2022

  15. [15]

    Sqa3d: Situated question answering in 3d scenes,

    X. Ma, S. Yong, Z. Zheng, Q. Li, Y . Liang, S.-C. Zhu, and S. Huang, “Sqa3d: Situated question answering in 3d scenes,” inInternational Conference on Learning Representations, 2023

    2023

  16. [16]

    ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop

    Y . Hong, J. Liu, H. Yin, M. Li, L. Guibas, F.-F. Li, J. Wu, and Y . Choi, “ESI-Bench: Towards embodied spatial intelligence that closes the perception–action loop,”arXiv preprint arXiv:2605.18746, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  17. [17]

    Aircopbench: A benchmark for multi-drone collaborative embodied perception and reasoning,

    J. Zha, Y . Fan, T. Zhang, G. Chen, Y . Chen, C. Gao, and X. Chen, “Aircopbench: A benchmark for multi-drone collaborative embodied perception and reasoning,” inProceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 2, 2026, pp. 1507–1515

    2026

  18. [18]

    MM-UA VBench: How well do multimodal large language models see, think, and plan in low-altitude uav scenarios?

    S. Dai, Z. Ma, Z. Luo, X. Yang, Y . Huang, W. Zhang, C. Chen, Z. Guo, W. Xu, Y . Sun, and M. Sun, “MM-UA VBench: How well do multimodal large language models see, think, and plan in low-altitude uav scenarios?” arXiv preprint arXiv:2512.23219, 2025

    work page arXiv 2025

  19. [19]

    Uavbench and uavit-1m: Benchmarking and enhancing mllms for low-altitude uav vision-language understanding,

    Y . Zhan and Y . Yuan, “Uavbench and uavit-1m: Benchmarking and enhancing mllms for low-altitude uav vision-language understanding,” arXiv preprint arXiv:2603.14336, 2026

    work page arXiv 2026

  20. [20]

    Are VLMs lost between sky and space? LinkS 2Bench for UA V- satellite dynamic cross-view spatial intelligence,

    D. Liu, J. Feng, D. Li, Y . Zheng, G. Li, W. Dong, and G. Shi, “Are vlms lost between sky and space? LinkS 2Bench for uav-satellite dynamic cross-view spatial intelligence,”arXiv preprint arXiv:2604.02020, 2026

    work page arXiv 2026

  21. [21]

    Cambrian-s: Towards spatial supersensing in video,

    S. Yang, J. Yang, P. Huang, E. L. Brown II, Z. Yang, Y . Yu, S. Tong, Z. Zheng, Y . Xu, M. Wanget al., “Cambrian-s: Towards spatial supersensing in video,” inThe Fourteenth International Conference on Learning Representations, 2026

    2026

  22. [22]

    arXiv preprint arXiv:2512.10863 , year=

    J. Lin, R. Xu, S. Zhu, S. Yang, P. Cao, Y . Ran, M. Hu, C. Zhu, Y . Xie, Y . Long, W. Hu, D. Lin, T. Wang, and J. Pang, “Mmsi-video-bench: A holistic benchmark for video-based spatial intelligence,”arXiv preprint arXiv:2512.10863, 2025

    work page arXiv 2025

  23. [23]

    EmbodiedCity: A benchmark platform for embodied agent in real-world city environment.arXiv preprint arXiv:2410.09604, 2024

    C. Gao, B. Zhao, W. Zhang, J. Mao, J. Zhang, Z. Zheng, F. Man, J. Fang, Z. Zhou, J. Cui, X. Chen, and Y . Li, “Embodiedcity: A benchmark platform for embodied agent in real-world city environment,”arXiv preprint arXiv:2410.09604, 2024

    work page arXiv 2024

  24. [24]

    Real-time and accurate uav pedestrian detection for social distancing monitoring in covid-19 pandemic,

    Z. Shao, G. Cheng, J. Ma, Z. Wang, J. Wang, and D. Li, “Real-time and accurate uav pedestrian detection for social distancing monitoring in covid-19 pandemic,”IEEE Transactions on Multimedia, vol. 24, pp. 2069–2083, 2022

    2069

  25. [25]

    UA VBench: An open benchmark dataset for autonomous and agentic ai uav systems via llm- generated flight scenarios,

    M. A. Ferrag, A. Lakas, and M. Debbah, “UA VBench: An open benchmark dataset for autonomous and agentic ai uav systems via llm- generated flight scenarios,”arXiv preprint arXiv:2511.11252, 2025

    work page arXiv 2025

  26. [26]

    Bedi: A comprehensive benchmark for evaluating embodied agents on uavs,

    M. Guo, M. Wu, J. He, S. Li, H. Li, and C. Tao, “Bedi: A comprehensive benchmark for evaluating embodied agents on uavs,”ISPRS Journal of Photogrammetry and Remote Sensing, vol. 232, pp. 910–936, 2026

    2026

  27. [27]

    Multiview aerial visual recognition (mavrec): Can multi-view improve aerial visual perception?

    A. Dutta, S. Das, J. Nielsen, R. Chakraborty, and M. Shah, “Multiview aerial visual recognition (mavrec): Can multi-view improve aerial visual perception?”arXiv preprint arXiv:2312.04548, 2023

    work page arXiv 2023

  28. [28]

    Airscape: An aerial generative world model with motion controllability,

    B. Zhao, R. Tang, M. Jia, Z. Wang, F. Man, X. Zhang, Y . Shang, W. Zhang, W. Wu, C. Gao, X. Chen, and Y . Li, “Airscape: An aerial generative world model with motion controllability,”arXiv preprint arXiv:2507.08885, 2025

    work page arXiv 2025

  29. [29]

    University-1652: A multi-view multi- source benchmark for drone-based geo-localization,

    Z. Zheng, Y . Wei, and Y . Yang, “University-1652: A multi-view multi- source benchmark for drone-based geo-localization,” inProceedings of the 28th ACM International Conference on Multimedia, 2020, pp. 1395–1403

    2020

  30. [30]

    Metric3d: Towards zero-shot metric 3d prediction from a single image,

    W. Yin, C. Zhang, H. Chen, Z. Cai, G. Yu, K. Wang, X. Chen, and C. Shen, “Metric3d: Towards zero-shot metric 3d prediction from a single image,” inProceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 9043–9053

    2023

  31. [31]

    Qwen3-VL Technical Report

    S. Bai, Y . Cai, R. Chen, K. Chen, X. Chen, Z. Cheng, L. Deng, W. Ding, C. Gao, C. Geet al., “Qwen3-vl technical report,”arXiv preprint arXiv:2511.21631, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  32. [32]

    InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

    W. Wang, Z. Gao, L. Gu, H. Pu, L. Cui, X. Wei, Z. Liu, L. Jing, S. Ye, J. Shaoet al., “Internvl3. 5: Advancing open-source multimodal models in versatility, reasoning, and efficiency,”arXiv preprint arXiv:2508.18265, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  33. [33]

    Scaling spatial intelligence with multimodal foundation models,

    Z. Cai, R. Wang, C. Gu, F. Pu, J. Xu, Y . Wang, W. Yin, Z. Yang, C. Wei, T. Zhouet al., “Scaling spatial intelligence with multimodal foundation models,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026, pp. 7879–7890

    2026

  34. [34]

    Spatial-mllm: Boosting mllm capabilities in visual-based spatial intelligence,

    D. Wu, F. Liu, Y .-H. Hung, and Y . Duan, “Spatial-mllm: Boosting mllm capabilities in visual-based spatial intelligence,”Advances in neural information processing systems, vol. 38, pp. 13 569–13 597, 2026

    2026

  35. [35]

    Visual spatial tuning.arXiv preprint arXiv:2511.05491,

    R. Yang, Z. Zhu, Y . Li, J. Huang, S. Yan, S. Zhou, Z. Liu, X. Li, S. Li, W. Wanget al., “Visual spatial tuning,”arXiv preprint arXiv:2511.05491, 2025

    work page arXiv 2025

  36. [36]

    Spatial understanding from videos: Structured prompts meet simulation data,

    H. Zhang, M. Liu, Z. Li, H. Wen, W. Guan, Y . Wang, and L. Nie, “Spatial understanding from videos: Structured prompts meet simulation data,”Advances in Neural Information Processing Systems, vol. 38, pp. 103 202–103 229, 2026

    2026

  37. [37]

    Spaceera++: A unified framework towards 3d spatial reasoning in video,

    W. Guan, H. Zhang, M. Liu, Q. Xiang, Y . Wang, and L. Nie, “Spaceera++: A unified framework towards 3d spatial reasoning in video,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

    2026

  38. [38]

    Qwen3 Technical Report

    A. Yang, A. Li, B. Yang, B. Zhang, B. Hui, B. Zheng, B. Yu, C. Gao, C. Huang, C. Lvet al., “Qwen3 technical report,”arXiv preprint arXiv:2505.09388, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025