Paper Citation Record · LEDGER

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

As of 5 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 71 inbound Pith citation observations for arXiv:2505.20279.

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

pith.paper-citation-record.v1
2505.20279 v5

Coverage vector

measured 95 of 95 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-19T12:54:01.013242Z

measured 166 of 166 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 71 of 71 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T20:38:55.151754Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

95 of 95 outbound references displayed

verified exact29
verified fuzzy63
unresolved3
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 288cff19-520e-4cfa-b0d2-7c93e1465652 · outbound

This paper cites an unresolved cited work.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-19T13:02:19.416499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d2fc3e26-dbaa-4493-a5a5-8f78ac1cf3e8 · outbound

This paper cites Specificity of learning: Why infants fall over a veritable cliff.Psychological Science, 11(4):290–295.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Specificity of learning: Why infants fall over a veritable cliff.Psychological Science, 11(4):290–295

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.395095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7e5e756-a79e-4fb7-b8ed-ef4fbfbbfd6b · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Flamingo: a visual language model for few-shot learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.390471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 639cbea1-0a31-4838-af80-3f66b605261b · outbound

This paper cites Scanqa: 3d question answering for spatial scene understanding.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Scanqa: 3d question answering for spatial scene understanding

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.370909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ce9edef-0c4f-464a-9457-60fab7defb66 · outbound

This paper cites Qwen Technical Report.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Qwen Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.946057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation af1f33da-af6b-41b8-8518-180d7e997bc4 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.937834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f4be9339-441c-49d9-a6de-86ce00b5b57c · outbound

This paper cites Qwen2.5-VL Technical Report.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Qwen2.5-VL Technical Report

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.971216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7df4d349-4fbd-4a94-b5af-b136e2a2bd04 · outbound

This paper cites ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.979751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ed22b408-5285-4d4d-a914-e5c3bcf60c0c · outbound

This paper cites Large Linguistic Models: Investigating LLMs' metalinguistic abilities.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Large Linguistic Models: Investigating LLMs' metalinguistic abilities

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.919160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 982e7e28-d815-48d4-9b1e-1abb639db716 · outbound

This paper cites Language models are few-shot learners.NeurIPS.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Language models are few-shot learners.NeurIPS

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.283045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db9b0fdf-6b0e-419c-98d0-760af2ad7471 · outbound

This paper cites Spatialvlm: Endow- ing vision-language models with spatial reasoning capabili- ties.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Spatialvlm: Endow- ing vision-language models with spatial reasoning capabili- ties

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.280271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 76bdf84f-f44b-44b6-bead-d5983a2b7160 · outbound

This paper cites Ll3da: Visual interactive instruction tuning for omni-3d understanding reasoning and planning.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Ll3da: Visual interactive instruction tuning for omni-3d understanding reasoning and planning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.277972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4a38ee90-8e7a-4a1b-be44-bb4fedba1558 · outbound

This paper cites Longvila: Scaling long-context vi- sual language models for long videos.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Longvila: Scaling long-context vi- sual language models for long videos.arXiv

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.275426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ec60a93-f700-414b-b19c-533701813241 · outbound

This paper cites How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites.Science China Information Sciences, 67(12):220101

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.450434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc7d53ed-46b1-451f-b050-68c2c4a909f5 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.447169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6180e137-9b41-42aa-b94d-628554fc5bda · outbound

This paper cites Spatial- rgpt: Grounded spatial reasoning in vision language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Spatial- rgpt: Grounded spatial reasoning in vision language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.444453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2c7c9a71-c1c5-4a81-b5bd-50c603d98855 · outbound

This paper cites Scannet: Richly-annotated 3d reconstructions of indoor scenes.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Scannet: Richly-annotated 3d reconstructions of indoor scenes

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.441733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e2097ed8-b3b4-4820-8212-72a6f32c502a · outbound

This paper cites 3d-llava: Towards generalist 3d lmms with omni superpoint transformer.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction 3d-llava: Towards generalist 3d lmms with omni superpoint transformer.arXiv

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.439059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 26ba6bdf-b15c-4173-86e0-16b7abba719e · outbound

This paper cites Palm-e: An embodied multimodal language model.arxiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Palm-e: An embodied multimodal language model.arxiv

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.435994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 91cc8df9-50c0-4aff-adee-bdc9dd7bf212 · outbound

This paper cites Large spatial model: End-to-end unposed images to semantic 3d.Advances in neural information processing systems, 37:40212–40229.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Large spatial model: End-to-end unposed images to semantic 3d.Advances in neural information processing systems, 37:40212–40229

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.433172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c163f6c-01ff-40f3-8fbc-9329d33b7fa5 · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.965601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f35a9cfc-7b31-49b3-85b6-8d2168020559 · outbound

This paper cites Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Video-mme: The first-ever comprehensive evaluation benchmark of multi-modal llms in video analysis

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.430621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ddd3158c-4c61-43b6-bba2-fb0f62201ce4 · outbound

This paper cites an unresolved cited work.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-05-19T13:02:19.428030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b22ee976-8d20-40a3-be7e-7adab94fe5e0 · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.425555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eef2d304-8096-4309-a9d5-7da150b0f885 · outbound

This paper cites Cascade cost volume for high-resolution 9 multi-view stereo and stereo matching.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Cascade cost volume for high-resolution 9 multi-view stereo and stereo matching

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.422187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b56cf3a5-89bd-42f3-b48f-6e0a5385f393 · outbound

This paper cites Cambridge university press.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Cambridge university press

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.419449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7b214bc-6fd8-4003-9ebc-9130ae929dcd · outbound

This paper cites Individual differences in spatial abilities.The Cambridge handbook of visuospatial thinking, pages 121–169.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Individual differences in spatial abilities.The Cambridge handbook of visuospatial thinking, pages 121–169

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.414137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 85ac9295-25a7-4836-aacc-09ec91d410e5 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Measuring Massive Multitask Language Understanding

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.976699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b959b21d-cfcc-4970-a531-70beba8b3ee1 · outbound

This paper cites 3d-llm: Inject- ing the 3d world into large language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction 3d-llm: Inject- ing the 3d world into large language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.411041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8956cff6-dc7b-4017-8ecf-7489da190266 · outbound

This paper cites Multiply: A multisensory object- centric embodied large language model in 3d world.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Multiply: A multisensory object- centric embodied large language model in 3d world

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.407256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0b072315-f3a0-41d2-80b2-c8005b6f7366 · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1(2):3.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Lora: Low-rank adaptation of large language models.ICLR, 1(2):3

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.404467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a36efbde-83f7-4cc1-945c-3f65fe7e747c · outbound

This paper cites Chat-scene: Bridging 3d scene and large language models with object identifiers.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Chat-scene: Bridging 3d scene and large language models with object identifiers

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.401520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c3fa2df-ace9-4161-b619-cff13a410cf1 · outbound

This paper cites Think- ing in dynamics: How multimodal large language models perceive, track, and reason dynamics in physical 4d world.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Think- ing in dynamics: How multimodal large language models perceive, track, and reason dynamics in physical 4d world

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.398597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 13b7a12b-88d9-40d8-9b2c-d6b87400b72e · outbound

This paper cites Gpt-4o system card.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Gpt-4o system card

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.392838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 176b21c4-a32a-48e2-82cd-5929fbabfabf · outbound

This paper cites GPT-4o System Card.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction GPT-4o System Card

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.934955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2c14db9d-9c5f-49d7-afa7-dfbbafa5de74 · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Scaling up visual and vision-language representation learning with noisy text supervision

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.387705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2397de9d-ad86-46d4-bfd0-59f3ea0cdc34 · outbound

This paper cites Language models with rationality.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Language models with rationality

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.384751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 92002432-7ab6-4ae7-9617-0f8d134f234f · outbound

This paper cites Ground- ing image matching in 3d with mast3r.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Ground- ing image matching in 3d with mast3r

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.382302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e1fb0817-cae5-436a-b16c-0832312d0733 · outbound

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

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction LLaVA-OneVision: Easy Visual Task Transfer

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.951456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a0edd5e1-3abc-409c-9775-a45302aaebb2 · outbound

This paper cites Llava-onevision: Easy visual task transfer.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Llava-onevision: Easy visual task transfer

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.379855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a92127dc-e1d9-4520-a9f7-5fd2aafb18a4 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.377361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4c4ae958-d758-4598-99ea-ad5c82545015 · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.374251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3b714487-2121-435b-a022-cf9295b61b17 · outbound

This paper cites Vila: On pre-training for visual language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Vila: On pre-training for visual language models

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.368407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f9fc90f-956d-4066-bb00-6a7ff5f040e0 · outbound

This paper cites Ost-bench: Evaluating the capabilities of mllms in online spatio-temporal scene understanding.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Ost-bench: Evaluating the capabilities of mllms in online spatio-temporal scene understanding

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.928522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4946b5cd-c496-47bd-9de3-29f191b7d7eb · outbound

This paper cites Visual instruction tuning.NeurIPS.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Visual instruction tuning.NeurIPS

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.366087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c77b11ea-bf67-4cfe-b28a-8fe3ed3e4a48 · outbound

This paper cites Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.995688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c2108898-ca17-4368-9202-129e1c1152ea · outbound

This paper cites Unified-io: A unified model for vision, language, and multi-modal tasks.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Unified-io: A unified model for vision, language, and multi-modal tasks.arXiv

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.363730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c627b4dc-78c6-4e8b-a85c-543e476b10c9 · outbound

This paper cites SQA3D: Situated Question Answering in 3D Scenes.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction SQA3D: Situated Question Answering in 3D Scenes

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.925336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f927bbe9-841f-456f-bae3-1d998d683bdc · outbound

This paper cites Openeqa: Embodied question answering in the era of foun- dation models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Openeqa: Embodied question answering in the era of foun- dation models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.360925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d43534f-83a9-4cf0-bd8e-23df09169d75 · outbound

This paper cites Spa- tiallm: Training large language models for structured in- door modeling.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Spa- tiallm: Training large language models for structured in- door modeling

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.932334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b5736758-3f31-4fac-a9f7-e3333cedabde · outbound

This paper cites How are the locations of objects in the environment represented in memory? InInternational conference on spatial cognition, pages 174–191.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction How are the locations of objects in the environment represented in memory? InInternational conference on spatial cognition, pages 174–191

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.358474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 19b0647b-b903-4de6-877a-00fbe927077d · outbound

This paper cites Individual differences in navigation: an introductory overview.Prime archives in psychology.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Individual differences in navigation: an introductory overview.Prime archives in psychology

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.355982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 283d2cf4-5cc5-4656-8047-51b32808da02 · outbound

This paper cites Mast3r-slam: Real-time dense slam with 3d reconstruction 10 priors.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Mast3r-slam: Real-time dense slam with 3d reconstruction 10 priors

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.353271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c43ae4d9-456b-4dae-a9f5-b21879f2b106 · outbound

This paper cites A Comprehensive Overview of Large Language Models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction A Comprehensive Overview of Large Language Models

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:28:39.632097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f66ca052-d8d4-409a-8fbb-064208529145 · outbound

This paper cites Kosmos-2: Grounding multimodal large language models to the world.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Kosmos-2: Grounding multimodal large language models to the world.arXiv

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.350951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f580f4c9-297d-4e79-9d3e-64ccb0abde5f · outbound

This paper cites Improving language understanding by gener- ative pre-training.OpenAI Blog.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Improving language understanding by gener- ative pre-training.OpenAI Blog

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.348497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 06d58fa1-eea7-43f7-92a0-5d7737e15429 · outbound

This paper cites Language models are unsu- pervised multitask learners.OpenAI blog, 1(8):9.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Language models are unsu- pervised multitask learners.OpenAI blog, 1(8):9

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.345965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1be725fc-8a8f-42d8-b96d-a4ba772a9216 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Learn- ing transferable visual models from natural language super- vision

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.343196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f9af211a-6592-49ff-9c64-2a7ff77b0f6e · outbound

This paper cites Habitat: A platform for embodied ai research.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Habitat: A platform for embodied ai research

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.340296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ab55bd1e-d896-4e6b-be9c-7d65a3ea14a1 · outbound

This paper cites Structure- from-motion revisited.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Structure- from-motion revisited

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.337960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d76d7748-9158-4771-b9a3-69c86b2fb3be · outbound

This paper cites MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.954380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dcb81cea-be14-4721-9888-3d547935b109 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Gemini: A Family of Highly Capable Multimodal Models

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.948707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a1ec1067-4ff1-4553-917d-b4d1fd4a3d83 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of con- text.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Gemini 1.5: Unlocking multimodal understanding across millions of tokens of con- text.arXiv

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.335354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2d0dd26b-8296-47f4-9ccb-fc0c0eba4d91 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction LLaMA: Open and Efficient Foundation Language Models

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.959632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a48a28e7-5e0c-45b7-b853-3485cc1dc09a · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.974006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a08a204b-1749-46f7-adf6-aac496c39be1 · outbound

This paper cites an unresolved cited work.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-05-19T13:02:19.333007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 03683f5f-842f-4921-9417-097cfe935b31 · outbound

This paper cites 3D Reconstruction with Spatial Memory.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction 3D Reconstruction with Spatial Memory

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.998536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8bfcbaab-93bb-47aa-a2c7-679f23797e2e · outbound

This paper cites Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.982684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2f1d1b15-0de5-45ac-8c0a-daec510929df · outbound

This paper cites VGGT: Visual Geometry Grounded Transformer.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction VGGT: Visual Geometry Grounded Transformer

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.992322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5d5fcb24-c093-4280-a9a8-5134bfc89e16 · outbound

This paper cites A survey on large language model based au- tonomous agents.Frontiers of Computer Science, 18(6): 186345.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction A survey on large language model based au- tonomous agents.Frontiers of Computer Science, 18(6): 186345

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.330759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6867501f-769a-4719-a96c-8430b0beb986 · outbound

This paper cites Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.328176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7f4afd21-f9f3-41f2-9cd6-eedb231e61ca · outbound

This paper cites Continuous 3D Perception Model with Persistent State.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Continuous 3D Perception Model with Persistent State

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.957147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 62118cfe-8cf9-414d-a5b3-bf7c7510b21f · outbound

This paper cites Dust3r: Geometric 3d vi- sion made easy.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Dust3r: Geometric 3d vi- sion made easy

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.325908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b87f94a7-a7f7-455e-a5ca-bb963b40f335 · outbound

This paper cites Emergent abilities of large language models.TMLR.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Emergent abilities of large language models.TMLR

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.323032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 464c7c19-7436-4453-817f-9704be2f3139 · outbound

This paper cites Dynamicverse: A physically- aware multimodal framework for 4d world modeling.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Dynamicverse: A physically- aware multimodal framework for 4d world modeling

Reference 75

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.943520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 075cb424-c74a-4abc-b2a4-31ba790d8c5d · outbound

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

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.988712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 381d89a9-f92c-435a-80ea-61ed73fb442d · outbound

This paper cites Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces

Reference 77

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.916212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f2f7711f-1566-4c1b-ae81-9b1467a86c9f · outbound

This paper cites Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.962691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c0e173d-c1f5-406a-a593-ae4c0d7b5607 · outbound

This paper cites Mvsnet: Depth inference for unstructured multi-view stereo.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Mvsnet: Depth inference for unstructured multi-view stereo

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.320163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ec9e627-5adf-4b66-b74c-86fbda9ac8b7 · outbound

This paper cites Scannet++: A high-fidelity dataset of 3d in- door scenes.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Scannet++: A high-fidelity dataset of 3d in- door scenes

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.317225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 04289116-dcf4-4568-9715-6b70ce94f633 · outbound

This paper cites Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Mmmu: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.313956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2bdd7e1f-26f0-429c-95fe-e645d9aab789 · outbound

This paper cites MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Reference 82

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.921894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation af60ba3e-af7f-46ec-887c-445a66aa29be · outbound

This paper cites Spatialstack: Layered geometry-language fusion for 3d vlm spatial reasoning.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Spatialstack: Layered geometry-language fusion for 3d vlm spatial reasoning

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.311221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ca71d35-d57a-46c1-b31b-74d6af952ada · outbound

This paper cites Long context transfer from language to vision.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Long context transfer from language to vision.arXiv

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.308776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cc288160-2790-4e00-b581-d2b03553eec8 · outbound

This paper cites Llava- next: A strong zero-shot video understanding model.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Llava- next: A strong zero-shot video understanding model

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.306070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9f3976c4-30c8-426f-a89b-b2cd0d54fcb2 · outbound

This paper cites LLaVA-Video: Video Instruction Tuning With Synthetic Data.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 86

Resolution: verified exact; local_arxiv, observed 2026-05-19T12:57:17.940393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7fc8ac22-0502-4f8b-832c-97fea333e413 · outbound

This paper cites Unveiling linguistic regions in large language mod- els.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Unveiling linguistic regions in large language mod- els

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.303448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0e73a075-a863-4f68-ac5a-18f3ac68fd2f · outbound

This paper cites Video-3d llm: Learning position-aware video representation for 3d scene understanding.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Video-3d llm: Learning position-aware video representation for 3d scene understanding.arXiv

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.300884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1afbfa50-2e6b-4cf1-8682-475436557316 · outbound

This paper cites Learning from videos for 3d world: Enhancing mllms with 3d vision geometry priors.arXiv preprint arXiv:2505.24625.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Learning from videos for 3d world: Enhancing mllms with 3d vision geometry priors.arXiv preprint arXiv:2505.24625

Reference 89

Resolution: verified exact; arxiv_id, observed 2026-05-19T12:57:17.985781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d4efdad9-bc2c-491b-8bea-7585c10c65a9 · outbound

This paper cites Video-3d llm: Learning position-aware video representation for 3d scene understanding.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Video-3d llm: Learning position-aware video representation for 3d scene understanding

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.298301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 30577fc6-a5f6-4ed3-9ead-8dac2f83a044 · outbound

This paper cites Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.295076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7e33c036-c44a-4149-b231-72d3b52bb796 · outbound

This paper cites Feature4x: Bridging any monocular video to 4d agentic ai with versatile gaussian feature fields.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Feature4x: Bridging any monocular video to 4d agentic ai with versatile gaussian feature fields

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.292195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7367b6aa-65a0-4729-a323-d1b27d74bcf5 · outbound

This paper cites Vlm4d: To- wards spatiotemporal awareness in vision language models.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Vlm4d: To- wards spatiotemporal awareness in vision language models

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.289863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1cfd3034-3377-453c-950e-c1aff81858b6 · outbound

This paper cites Llava-3d: A simple yet effective pathway to empowering lmms with 3d-awareness.arXiv.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction Llava-3d: A simple yet effective pathway to empowering lmms with 3d-awareness.arXiv

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.287629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c92deb70-9b8e-4a07-971f-6e7b8f9ad8d1 · outbound

This paper cites cut3r"). •Spatial tower feature selection:all (-spatial_tower_select_feature.

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction cut3r"). •Spatial tower feature selection:all (-spatial_tower_select_feature

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T13:02:19.285410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation 1748d8d8-dcb6-4c53-96ee-9ac2ae4ff15a · inbound

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling cites this paper.

Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-19T05:17:06.515129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 18e16956-dcb9-415c-98e7-ffb48e60eabc · inbound

MiMo-Embodied: X-Embodied Foundation Model Technical Report cites this paper.

MiMo-Embodied: X-Embodied Foundation Model Technical Report VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-17T20:42:05.749042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8beef7b3-9c22-424a-9346-c780f52d2a60 · inbound

POMA-3D: The Point Map Way to 3D Scene Understanding cites this paper.

POMA-3D: The Point Map Way to 3D Scene Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-17T20:30:11.587250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b37eb10-8f7d-4afa-a7bd-7b914bb2bdd3 · inbound

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention cites this paper.

AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-17T06:29:09.920022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 72fc96a9-1852-4a86-a0bd-ed1dcd958dde · inbound

MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images cites this paper.

MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T20:38:55.151754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21301638-439e-4870-8602-cdf4736ed86b · inbound

Vision-Language Memory for Spatial Reasoning cites this paper.

Vision-Language Memory for Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T20:15:31.896130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ce4afd6-147d-4bd5-84f1-9cdda824591c · inbound

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics cites this paper.

Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T16:27:29.726654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1831e13-f921-45a6-bf70-d21f12765136 · inbound

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation cites this paper.

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-16T21:21:16.837689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f3930752-0673-4b19-bf00-18b286a6e413 · inbound

SpatialMosaic: A Multiview VLM Dataset for Partial Visibility cites this paper.

SpatialMosaic: A Multiview VLM Dataset for Partial Visibility VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T19:43:20.635922Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c41cab4d-fb61-4081-a3a1-95893414ea94 · inbound

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning cites this paper.

Thinking with Geometry: Active Geometry Integration for Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:40:42.249141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation da88302d-5f16-4054-a7fa-7860c3ea0ee1 · inbound

From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models cites this paper.

From Correspondence to Actions: Human-Like Multi-Image Spatial Reasoning in Multi-modal Large Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-03T03:16:49.980712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

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

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 52691746-4362-4d09-b91e-28edaf28870f · inbound

Lifting Unlabeled Internet-level Data for 3D Scene Understanding cites this paper.

Lifting Unlabeled Internet-level Data for 3D Scene Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-13T22:18:21.027476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a8a92a83-2a37-4d29-9491-ddb7fae99dd0 · inbound

Token Warping Helps MLLMs Look from Nearby Viewpoints cites this paper.

Token Warping Helps MLLMs Look from Nearby Viewpoints VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-13T21:08:17.319333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9540fc1d-5bca-4c5f-baa7-747a4ab62bfb · inbound

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs cites this paper.

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-13T22:43:22.849324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6304c5ad-c398-44bc-a868-2b2cec354c16 · inbound

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs cites this paper.

EgoMind: Activating Spatial Cognition through Linguistic Reasoning in MLLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T14:39:55.177552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59ef32d2-5eae-40c0-ab84-b4d452b401e4 · inbound

Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs cites this paper.

Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-10T22:50:48.937546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e775d07-3f13-4c16-8a62-3d50c5bdac36 · inbound

OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence cites this paper.

OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T06:20:56.452510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 988ed2c0-e3b9-4738-b948-e4023014ec2a · inbound

MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding cites this paper.

MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:51:22.687350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 208a0fa6-3e3a-41ec-92d0-ee4dfb2f89f6 · inbound

EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks cites this paper.

EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-11T07:26:02.915690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b7a3b696-8d0f-4da9-99d8-6762a4fe11bb · inbound

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents cites this paper.

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T07:51:01.840538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 669f4dd9-308c-4e4f-b456-43437c4d6cb5 · inbound

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents cites this paper.

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T23:07:40.699400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cd39307-67d1-4280-a214-54ed885adc0a · inbound

FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views cites this paper.

FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:05:59.356995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5148c8c7-2edf-4964-bdd9-757a2185c3e0 · inbound

Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale cites this paper.

Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T08:45:59.615137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c6c57998-7704-4748-ba5c-7844ba140ca5 · inbound

SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning cites this paper.

SpatialImaginer: Towards Adaptive Visual Imagination for Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-10T06:41:37.173534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation abf82160-1912-4bee-bb4f-9d665413e1bc · inbound

$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills cites this paper.

$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-11T22:11:15.955057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7d95985a-5bfc-45e6-9901-549d7b439c0e · inbound

$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills cites this paper.

$M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T18:17:43.564400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56513e2-ee0b-438f-95ff-6b0c9f902ef0 · inbound

From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs cites this paper.

From Where Things Are to What They Are For: Benchmarking Spatial-Functional Intelligence in Multimodal LLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T16:26:07.551530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ba8aabf-f7a2-4852-ae40-767ea41d21eb · inbound

4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding cites this paper.

4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:41:11.622389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7b1db54e-df36-495e-8276-412ce2a58024 · inbound

4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding cites this paper.

4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-25T06:16:39.987125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9daa15a9-0708-4dc3-a37e-eee7b909be5b · inbound

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models cites this paper.

ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-12T06:46:36.484052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4b6c8d52-2ab3-43dc-a562-34b6ec611bd7 · inbound

Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence cites this paper.

Thinking with Novel Views: A Systematic Analysis of Generative-Augmented Spatial Intelligence VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-12T03:26:19.434881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cb433cfb-8682-4833-960d-027191258f21 · inbound

Unlocking Dense Metric Depth Estimation in VLMs cites this paper.

Unlocking Dense Metric Depth Estimation in VLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:23:40.983094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a871081d-438e-475e-83b5-81e377616e16 · inbound

Unlocking Dense Metric Depth Estimation in VLMs cites this paper.

Unlocking Dense Metric Depth Estimation in VLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:59:51.135163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2af36fcf-4064-4925-a018-20e654f26702 · inbound

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop cites this paper.

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T10:53:13.231273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78c983b0-1385-49ef-8794-399535244996 · inbound

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop cites this paper.

ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T15:05:47.166596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a01ac1f-6c16-4883-8bf5-7a95a003cd18 · inbound

Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs cites this paper.

Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-20T06:33:05.687991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation de6b68d9-e1e1-43f7-97a1-4e02afaee201 · inbound

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models cites this paper.

CaMo: Camera Motion Grounded Evaluation and Training for Vision-Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T05:28:04.482966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cd044ad7-e6bb-41fe-869f-895663ee4ec4 · inbound

GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning cites this paper.

GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:24:43.013284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0d1b0f23-44eb-4190-aae2-67b781e2cf15 · inbound

FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand cites this paper.

FOUND-IT: Foundation-model-first Task-driven 3D Scene Graphs with Granularity on Demand VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:14:00.409776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 65344bf0-5fc9-41cb-a2fb-ba53442bd7f1 · inbound

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs cites this paper.

ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:23:59.822765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc22489d-b3ad-44fa-b356-3890aac17da1 · inbound

Rethinking VLM Representation for VLA Initialization cites this paper.

Rethinking VLM Representation for VLA Initialization VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:24:00.117539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 02ae9c95-43bc-457a-9ec5-5106e037d117 · inbound

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning cites this paper.

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T18:23:51.003446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 410835b6-7d69-46ff-b0b7-0d3755c92003 · inbound

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning cites this paper.

Q-GeoMem: Question-Guided Geometric Memory for Video Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T15:54:12.909974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ad13a23-9cba-4100-a90f-dd043cf2f2db · inbound

GEM: Generative Supervision Helps Embodied Intelligence cites this paper.

GEM: Generative Supervision Helps Embodied Intelligence VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T13:43:28.785956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 836f2d3b-50e8-4b3f-9ee7-e0b3200285d5 · inbound

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning cites this paper.

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T07:53:13.591518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a5efadf7-31ca-43a6-8bbf-9a9b7633b7db · inbound

VLM3: Vision Language Models Are Native 3D Learners cites this paper.

VLM3: Vision Language Models Are Native 3D Learners VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T07:53:14.035073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d4695e3-ec45-4763-b24e-d4daa812bde7 · inbound

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning cites this paper.

Reasmory: 3D Reconstruction as Explicit Memory for VLMs Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-01T20:46:13.705434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 172430c8-6156-4f93-b18f-16d0396fe560 · inbound

LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video cites this paper.

LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:16:57.284944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 97f70fd8-d53f-49d8-95d7-7d4ff37a028d · inbound

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models cites this paper.

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:16:57.501253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2ad5078d-463c-4a61-8820-64f322518b5e · inbound

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators cites this paper.

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:06:56.185660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c8b7796c-cea6-4bb4-a106-b26f1bb6a626 · inbound

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors cites this paper.

Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:17:09.596982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 49f4cc9a-3a38-4f48-a4cc-9fbf10a12dba · inbound

MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model cites this paper.

MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-07-02T21:57:25.759560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 005223eb-9046-492a-bdcc-9e2bad9af23d · inbound

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models cites this paper.

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-03T06:07:41.198931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 96c73d22-5ff5-409a-b42d-5c9ea1ff33c1 · inbound

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models cites this paper.

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-06-27T13:10:56.965482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 769b4eb0-af1d-4d83-9d63-b66266a758b5 · inbound

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models cites this paper.

Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-14T18:07:09.018997Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebd187e6-062b-4691-82ef-abcb8fe59e2c · inbound

4DP-QA: Scalable QA for 4D Perception in Vision Language Models cites this paper.

4DP-QA: Scalable QA for 4D Perception in Vision Language Models VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-03T08:17:45.089423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 176e599f-f951-4c2f-b405-889d38af0ada · inbound

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning cites this paper.

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:17:48.664257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4736f1a5-253d-44b8-aeaa-f8ed487e9985 · inbound

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning cites this paper.

Ouroboros-Spatial: Closing the Data-Model Loop for Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T11:51:33.410398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecf77e8a-a6be-4908-aff0-fa8ba5799aed · inbound

Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views cites this paper.

Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-04T10:39:45.344628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1520916c-287b-4dee-8ae8-afd507451ec0 · inbound

HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory cites this paper.

HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-04T10:49:46.507869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 019ffe8c-56e7-4c01-8659-fb28a604c152 · inbound

Natural Language Camera Movement Understanding cites this paper.

Natural Language Camera Movement Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T05:16:19.750976Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d6508d-02ce-49ee-b531-beff7c611609 · inbound

ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI cites this paper.

ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 157

Resolution: unresolved; no resolver link, observed 2026-07-11T19:16:57.396710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5130446-0bca-45bf-bbb3-b20c569965ec · inbound

GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding cites this paper.

GeoAnchor: Collaborative Reasoning via Latent Decomposition for 3D Spatial Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T05:13:00.188880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a027346-4e82-4a16-966d-da6358e1aa4e · inbound

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding cites this paper.

Beyond Single Expert: Harmonizing Diverse Visual Priors in MLLMs for Spatial Understanding VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T00:23:01.277839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16e7b789-74c0-470a-b4fb-88a0ae418c67 · inbound

LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning cites this paper.

LenGuard-GPC: Length Guarding with Guided-Prompt Consistency for Spatial Reasoning Reinforce Learning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-01T18:40:13.176413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa0a7a7-c2fc-46e4-9139-d2db48040c5a · inbound

ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning cites this paper.

ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T17:36:37.411186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ca5a98-8e67-494d-91a3-64c1160421e3 · inbound

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model cites this paper.

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T16:32:47.404785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f46a6b-c319-4bc8-8a57-883213c90388 · inbound

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model cites this paper.

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T01:57:28.855191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b57eb1c8-c706-43c6-9117-8cb5704b1a7c · inbound

ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes? cites this paper.

ViSTR-Bench: Can MLLMs Reason from Continuous Visual Cues in Dynamic Scenes? VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-01T09:09:24.856306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c8bbc7-3954-478e-bafd-bb833e4922bd · inbound

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text cites this paper.

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T08:39:37.227319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.