Paper Citation Record · LEDGER

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

As of 22 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 1 inbound Pith citation observation for arXiv:2603.16461.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2603.16461 v2

Coverage vector

measured 61 of 61 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T18:06:09.998507Z

measured 62 of 62 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-07T13:45:53.346402Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-12T08:46:26.794017Z

Reference resolution

61 of 61 outbound references displayed

verified exact0
verified fuzzy0
unresolved61
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1fcca2d3-6baa-47b7-8752-d99503cc7058 · outbound

This paper cites In: European conference on computer vision.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: European conference on computer vision

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.807506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 588d605b-4154-431c-985a-d2060adfd6fe · outbound

This paper cites Qwen3-VL Technical Report.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Qwen3-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.811884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15bb0ec-165c-4d4c-a020-de0815af47f5 · outbound

This paper cites Qwen2.5-VL Technical Report.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.815651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25a8376b-b6bb-462f-8fe2-911d0a8d9ffd · outbound

This paper cites arXiv preprint arXiv:2509.25413 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2509.25413 (2025)

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.819064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47a236d9-50b0-4486-9aa9-2dd88e24b991 · outbound

This paper cites arXiv preprint arXiv:2410.01647 (2024).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2410.01647 (2024)

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.822371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d91e9bb2-c90b-47e9-995b-1e675a7f17e5 · outbound

This paper cites arXiv preprint arXiv:2603.00912 (2026).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2603.00912 (2026)

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.825904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9d2f36b-d8fd-44fa-af04-709617b99728 · outbound

This paper cites Advances in Neu- ral Information Processing Systems36, 71862–71873 (2023).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Advances in Neu- ral Information Processing Systems36, 71862–71873 (2023)

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.829387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1e9b0cd-778b-47c5-bfb4-bb6f69abcef3 · outbound

This paper cites IEEE Transactions on Pattern Analysis and Machine Intelligence (2025) 16 J.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models IEEE Transactions on Pattern Analysis and Machine Intelligence (2025) 16 J

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.832361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54160019-3dae-432b-aaec-93892e3d85f5 · outbound

This paper cites In: ECCV (2020).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: ECCV (2020)

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.835431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8eb9a3c-6c97-408b-94bb-96d489c796a1 · outbound

This paper cites an unresolved cited work.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.838718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 865af6f7-82c8-426b-b558-9455f2c59ac4 · outbound

This paper cites In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.841836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed21cab-d60b-4396-8cd9-23f130b683c3 · outbound

This paper cites Grounded 3D-LLM with Referent Tokens.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Grounded 3D-LLM with Referent Tokens

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.844829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f64a274-e475-47fe-b58a-bd512e9662a3 · outbound

This paper cites arXiv preprint arXiv:2510.13800 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2510.13800 (2025)

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.848516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65e5a41c-1917-4984-9027-4369647c380a · outbound

This paper cites In: Proceedings of the IEEE/CVF conference on com- puter vision and pattern recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF conference on com- puter vision and pattern recognition

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.851409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1652069e-2d10-4ccb-b348-c4396a15c58b · outbound

This paper cites In: Proceedings of the IEEE/CVF international conference on computer vision.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF international conference on computer vision

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.854350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6760b3f-42a1-4d6a-b51e-d5f753e5cbc7 · outbound

This paper cites In: Proceedings of the IEEE conference on computer vision and pattern recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE conference on computer vision and pattern recognition

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.857411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc177dd-407d-4269-87e4-f8868b2ef40c · outbound

This paper cites Generating Context-Aware Natural Answers for Questions in 3D Scenes.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Generating Context-Aware Natural Answers for Questions in 3D Scenes

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.860375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ecc57ab-2221-4b00-8e81-684fbf08f0ed · outbound

This paper cites VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.863681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bde5895-7a6b-4d60-ab7c-f20a72793119 · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.866812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a134d4a-f2a0-4caa-bd2a-39920d8eadf3 · outbound

This paper cites arXiv preprint arXiv:2601.11442 (2026).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2601.11442 (2026)

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.870167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3efb21c4-a27f-4919-9719-3a056ab52254 · outbound

This paper cites Cambridge university press (2003).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Cambridge university press (2003)

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.872927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 198bf949-7719-4d36-8145-8662a659a0c8 · outbound

This paper cites Advances in Neural Information Processing Systems36, 20482–20494 (2023).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Advances in Neural Information Processing Systems36, 20482–20494 (2023)

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.875787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4faea79-27b4-400f-8d07-ef075bd40540 · outbound

This paper cites Advances in Neural Information Processing Systems 37, 113991–114017 (2024).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Advances in Neural Information Processing Systems 37, 113991–114017 (2024)

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.878556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98843dd9-ff48-49ea-855b-63b32843dc1f · outbound

This paper cites An Embodied Generalist Agent in 3D World.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models An Embodied Generalist Agent in 3D World

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.881685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 900369b8-9543-4269-95d4-364584a09cd7 · outbound

This paper cites GPT-4o System Card.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models GPT-4o System Card

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.884802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ae736e-4d64-4c03-82b2-9b1a1fc80846 · outbound

This paper cites MapAnything: Universal Feed-Forward Metric 3D Reconstruction.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.887988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d9e8f8-8ab9-47af-bb2e-9b7deed37f30 · outbound

This paper cites OpenVLA: An Open-Source Vision-Language-Action Model.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models OpenVLA: An Open-Source Vision-Language-Action Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.891673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c711c68-0cd5-4ef3-98d1-cbe8c254770f · outbound

This paper cites Unified Semantic Transformer for 3D Scene Understanding.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Unified Semantic Transformer for 3D Scene Understanding

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.895072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b970326-5b68-49a3-9c94-3448979b1a73 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.898270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d1d639-d6e9-4f89-9fd7-6ca76690e7d7 · outbound

This paper cites arXiv preprint arXiv:2510.22706 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2510.22706 (2025)

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.901428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ddf83bc-5c11-4ff4-8d26-92fcb9e5b908 · outbound

This paper cites In: International conference on machine learning.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: International conference on machine learning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.904718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2048f2-77fc-4502-be11-51f8fd6b0096 · outbound

This paper cites Depth Anything 3: Recovering the Visual Space from Any Views.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Depth Anything 3: Recovering the Visual Space from Any Views

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.907725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1939b48-2b0a-46e4-ab41-826f6277cc82 · outbound

This paper cites arXiv preprint arXiv:2405.10255 (2024).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2405.10255 (2024)

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.910861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0db83715-bbc9-488e-a1a5-06f8bbdab8dc · outbound

This paper cites In: Ad- vances in Neural Information Processing Systems (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Ad- vances in Neural Information Processing Systems (2025)

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.914100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f23dd2db-0b40-466f-9558-fc66b03e51eb · outbound

This paper cites Ad- vances in Neural Information Processing Systems37, 23464–23487 (2024).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Ad- vances in Neural Information Processing Systems37, 23464–23487 (2024)

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.917331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b22861a-8f8a-46fd-b74a-89800da0ddc2 · outbound

This paper cites In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.920391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db357836-d2ad-4316-87a1-1dac645ee97f · outbound

This paper cites In: proceedings of the IEEE/CVF International Conference on Computer Vision.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: proceedings of the IEEE/CVF International Conference on Computer Vision

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.923398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ee15ea0-69cc-44c5-9b2c-8fcee3ae62f6 · outbound

This paper cites GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.926358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15d34ea-ab75-40ff-903a-ad20c3dda213 · outbound

This paper cites SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.930155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eacb1e50-027d-460a-8a57-898cd3310017 · outbound

This paper cites In: International conference on machine learning.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: International conference on machine learning

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.933431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 326b211d-d163-4176-b133-6e05c5826e14 · outbound

This paper cites In: Proceedings of the IEEE conference on computer vision and pattern recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE conference on computer vision and pattern recognition

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.936478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1a76a0-11b3-4788-8627-18c2e0d58dcd · outbound

This paper cites FastVGGT: Training-Free Acceleration of Visual Geometry Transformer.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models FastVGGT: Training-Free Acceleration of Visual Geometry Transformer

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.939650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d43fbef-8407-46c1-a296-a98901fcaeef · outbound

This paper cites arXiv preprint arXiv:2505.23044 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2505.23044 (2025)

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.943321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f6bd746-e000-4fc3-b695-c9b154cf2774 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.946206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8811f6d-b96f-4be4-908d-793fcdd8b17a · outbound

This paper cites arXiv preprint arXiv:2511.18416 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2511.18416 (2025)

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.949484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ad40dd2-a235-4352-8aa0-e4fa2126fb4d · outbound

This paper cites In: Proceedings of the Computer Vision and Pattern Recognition Conference.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the Computer Vision and Pattern Recognition Conference

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.952498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2c85b51-1ce0-4a92-aff2-fab8181a1f78 · outbound

This paper cites In: Proceedings of the Computer Vision and Pattern Recognition Conference.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the Computer Vision and Pattern Recognition Conference

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.955607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0833805c-8384-4d0d-8a36-13af845644f8 · outbound

This paper cites In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.958696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a629d8d-6cb2-4e7c-86c7-512679084b05 · outbound

This paper cites In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.961597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51656720-c56f-4e2d-9d4c-ac62b7aa7b21 · outbound

This paper cites $\pi^3$: Permutation-Equivariant Visual Geometry Learning.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models $\pi^3$: Permutation-Equivariant Visual Geometry Learning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.964640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68d5ae86-8032-4c38-8bb0-745e36e66c59 · outbound

This paper cites Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.967760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a8323a6-c07f-4d7a-b729-77691eb92f5a · outbound

This paper cites arXiv preprint arXiv:2508.11952 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2508.11952 (2025)

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.970802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d383857f-9b51-417f-b0ad-bd974ab490f3 · outbound

This paper cites In: Pro- ceedings of the Computer Vision and Pattern Recognition Conference.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Pro- ceedings of the Computer Vision and Pattern Recognition Conference

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.973850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79cf545c-addb-4ace-9c0f-ae7939298575 · outbound

This paper cites arXiv preprint arXiv:2511.05491 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2511.05491 (2025)

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.976837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d77854-2572-4d74-804c-64e05ccdb025 · outbound

This paper cites arXiv preprint arXiv:2601.02281 (2026).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2601.02281 (2026)

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.979716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 154fce46-323e-4dc9-9ba1-038e1a5b9367 · outbound

This paper cites arXiv preprint arXiv:2503.22976 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2503.22976 (2025)

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.982621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e2179d-74d7-4342-9ece-3a69ed43b3fd · outbound

This paper cites arXiv preprint arXiv:2505.24625 (2025).

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2505.24625 (2025)

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.985621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6c37f8d-50d4-47e7-84f0-4a726b9ed11a · outbound

This paper cites In: Proceedings of the Computer Vision and Pattern Recognition Conference.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models In: Proceedings of the Computer Vision and Pattern Recognition Conference

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.989175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 046d1603-6434-4f23-b3ef-35111921709d · outbound

This paper cites arXiv preprint arXiv:2510.25760 (2025) GAP-MLLM 19.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models arXiv preprint arXiv:2510.25760 (2025) GAP-MLLM 19

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.992189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78606104-cf6a-4120-8cd3-97f27074cf27 · outbound

This paper cites LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.995051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e7adcd3-e2ef-4b33-af1b-ab9fc07ef5a2 · outbound

This paper cites label"and the point’s 3D coordinate in.

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models label"and the point’s 3D coordinate in

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T18:06:09.998507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d237b7b1-64a0-4574-a2ca-0b54252f643b · inbound

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness cites this paper.

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-07-21T02:21:33.200827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.