Paper Citation Record · LEDGER

Test3R: Learning to Reconstruct 3D at Test Time

As of 7 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 2 inbound Pith citation observations for arXiv:2506.13750.

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

pith.paper-citation-record.v1
2506.13750 v1

Coverage vector

measured 68 of 68 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:32:08.417157Z

measured 70 of 70 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:23:09.928240Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T11:20:11.282375Z

Reference resolution

68 of 68 outbound references displayed

verified exact1
verified fuzzy31
unresolved36
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 04865b96-d4d3-4185-a666-cd8623e9a09b · outbound

This paper cites D2-net: A trainable cnn for joint description and detection of local features.

Test3R: Learning to Reconstruct 3D at Test Time D2-net: A trainable cnn for joint description and detection of local features

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.655826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b405b583-41f9-43a8-986d-390496f0fbeb · outbound

This paper cites Superpoint: Self-supervised interest point detection and description.

Test3R: Learning to Reconstruct 3D at Test Time Superpoint: Self-supervised interest point detection and description

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.645658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 50cb39df-083a-42a1-a013-059fd1576e25 · outbound

This paper cites Distinctive image features from scale-invariant keypoints.

Test3R: Learning to Reconstruct 3D at Test Time Distinctive image features from scale-invariant keypoints

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:04.556466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd274ab-2b63-4d17-a9ae-f0b7a03842c6 · outbound

This paper cites Neural-guided ransac: Learning where to sample model hypotheses.

Test3R: Learning to Reconstruct 3D at Test Time Neural-guided ransac: Learning where to sample model hypotheses

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.626819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7d10c04c-0919-40d5-8ca9-b9410c643dee · outbound

This paper cites Lightglue: Local feature matching at light speed.

Test3R: Learning to Reconstruct 3D at Test Time Lightglue: Local feature matching at light speed

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.616247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation aa2b0864-4f8e-4b0d-8f2f-86a2d2ae91b6 · outbound

This paper cites Progressive correspondence pruning by consensus learning.

Test3R: Learning to Reconstruct 3D at Test Time Progressive correspondence pruning by consensus learning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.605869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c50178f3-a061-4eb1-a8ec-c5399079a83e · outbound

This paper cites Sfm with mrfs: Discrete- continuous optimization for large-scale structure from motion.

Test3R: Learning to Reconstruct 3D at Test Time Sfm with mrfs: Discrete- continuous optimization for large-scale structure from motion

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.594993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 76213e0c-9a39-447e-b57c-7d29c2042265 · outbound

This paper cites Pixel-perfect structure- from-motion with featuremetric refinement.

Test3R: Learning to Reconstruct 3D at Test Time Pixel-perfect structure- from-motion with featuremetric refinement

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.584689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eaacd2ae-1dbc-4b04-801f-05d02da57ec0 · outbound

This paper cites Structure-from-motion revisited.

Test3R: Learning to Reconstruct 3D at Test Time Structure-from-motion revisited

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.043280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1362ba9-6870-45da-b9db-71439f53f5a2 · outbound

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

Test3R: Learning to Reconstruct 3D at Test Time Cascade cost volume for high-resolution multi-view stereo and stereo matching

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.567023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba2ebcaf-3259-4a36-9ab1-36fea13361cc · outbound

This paper cites Pixelwise view selection for unstructured multi-view stereo.

Test3R: Learning to Reconstruct 3D at Test Time Pixelwise view selection for unstructured multi-view stereo

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.556305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5066e2cd-467a-460a-9da0-650c12ddadaa · outbound

This paper cites Dust3r: Geometric 3d vision made easy.

Test3R: Learning to Reconstruct 3D at Test Time Dust3r: Geometric 3d vision made easy

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.241429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05f6cd91-b0dc-44d3-878c-d89d4eb18abe · outbound

This paper cites Grounding image matching in 3d with mast3r.

Test3R: Learning to Reconstruct 3D at Test Time Grounding image matching in 3d with mast3r

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.313570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d3c2144-ed35-4161-9819-b8f2a1538b51 · outbound

This paper cites A multiple-baseline stereo.

Test3R: Learning to Reconstruct 3D at Test Time A multiple-baseline stereo

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.530369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 341a91b7-4d98-46c4-953e-cbb615b95e86 · outbound

This paper cites Visual prompt tuning.

Test3R: Learning to Reconstruct 3D at Test Time Visual prompt tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.519753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d0ac0ee0-46ee-4c40-96f9-ad69613a6b62 · outbound

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

Test3R: Learning to Reconstruct 3D at Test Time MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.524753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e14c3fdb-759d-4c25-aa40-270bb1fbd55d · outbound

This paper cites The interpretation of structure from motion.

Test3R: Learning to Reconstruct 3D at Test Time The interpretation of structure from motion

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.508990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e822f2df-8441-4862-9f7d-c7df5d0c9f08 · outbound

This paper cites Multi-view stereo: A tutorial.

Test3R: Learning to Reconstruct 3D at Test Time Multi-view stereo: A tutorial

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.631350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9127d532-c1db-4a83-9749-7ee0fa6da606 · outbound

This paper cites Massively parallel multiview stereopsis by surface normal diffusion.

Test3R: Learning to Reconstruct 3D at Test Time Massively parallel multiview stereopsis by surface normal diffusion

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.695439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13e4d071-9b92-4180-a773-c0ec0f9b64e5 · outbound

This paper cites Adaptive patch deformation for textureless-resilient multi-view stereo.

Test3R: Learning to Reconstruct 3D at Test Time Adaptive patch deformation for textureless-resilient multi-view stereo

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.483150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8483674-83e6-4e9e-8ade-a22eceb9c54a · outbound

This paper cites Geo-neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction.

Test3R: Learning to Reconstruct 3D at Test Time Geo-neus: Geometry-consistent neural implicit surfaces learning for multi-view reconstruction

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.472013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f4453242-d554-4c29-82e3-ec3d56600bfd · outbound

This paper cites Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision.

Test3R: Learning to Reconstruct 3D at Test Time Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervision

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.460371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 48eb0c14-45b5-44d0-a5b1-e3e454e988c8 · outbound

This paper cites Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo.

Test3R: Learning to Reconstruct 3D at Test Time Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.449213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 170c5e92-068f-4eff-b08c-4b19a49ad143 · outbound

This paper cites Multiview neural surface reconstruction by disentangling geometry and appearance.

Test3R: Learning to Reconstruct 3D at Test Time Multiview neural surface reconstruction by disentangling geometry and appearance

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:05.994727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aed3c46-39c3-4338-94e1-45a9cd883f06 · outbound

This paper cites Multiview stereo with cascaded epipolar raft.

Test3R: Learning to Reconstruct 3D at Test Time Multiview stereo with cascaded epipolar raft

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.430953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cab40be3-91ed-4812-8206-4b02fb11d2ec · outbound

This paper cites Rethinking depth estimation for multi-view stereo: A unified representation.

Test3R: Learning to Reconstruct 3D at Test Time Rethinking depth estimation for multi-view stereo: A unified representation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.420334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6f0f8482-690a-4eb9-9ded-2d968066433e · outbound

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

Test3R: Learning to Reconstruct 3D at Test Time Mvsnet: Depth inference for unstructured multi-view stereo

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.186189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ace77ee4-b69b-41eb-82d0-a7e7373231b6 · outbound

This paper cites Geomvsnet: Learning multi-view stereo with geometry perception.

Test3R: Learning to Reconstruct 3D at Test Time Geomvsnet: Learning multi-view stereo with geometry perception

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.275869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e945b7ed-c03b-457b-89d6-32e96b981d73 · outbound

This paper cites VGGT: Visual Geometry Grounded Transformer.

Test3R: Learning to Reconstruct 3D at Test Time VGGT: Visual Geometry Grounded Transformer

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.332826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26147945-52da-4f2d-8c8a-dfe064cf5c5e · outbound

This paper cites SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos.

Test3R: Learning to Reconstruct 3D at Test Time SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.416651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f5d0c28-2107-40c4-8b50-45ace5b50c97 · outbound

This paper cites 3D Reconstruction with Spatial Memory.

Test3R: Learning to Reconstruct 3D at Test Time 3D Reconstruction with Spatial Memory

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.497884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 468a1c6e-e58b-405b-93be-d4e940af0588 · outbound

This paper cites Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors.

Test3R: Learning to Reconstruct 3D at Test Time Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.591511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf16062e-cb89-48a1-bd3e-67ffda8276b3 · outbound

This paper cites Align3R: Aligned Monocular Depth Estimation for Dynamic Videos.

Test3R: Learning to Reconstruct 3D at Test Time Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.656226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487f076a-92ba-435a-81c2-ac75e9465c13 · outbound

This paper cites Easi3r: Estimating disentangled motion from dust3r without training.

Test3R: Learning to Reconstruct 3D at Test Time Easi3r: Estimating disentangled motion from dust3r without training

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.701380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c7f0fc5-d77d-4e87-b382-5f3698c6912f · outbound

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

Test3R: Learning to Reconstruct 3D at Test Time Continuous 3D Perception Model with Persistent State

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.778222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1d3b104-aae9-434e-9fa1-2337d3787953 · outbound

This paper cites Gflow: Recovering 4d world from monocular video.

Test3R: Learning to Reconstruct 3D at Test Time Gflow: Recovering 4d world from monocular video

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.393872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f1a7a62d-2d5c-47b7-92dc-4e6711d53337 · outbound

This paper cites Pe3r: Perception-efficient 3d reconstruction.

Test3R: Learning to Reconstruct 3D at Test Time Pe3r: Perception-efficient 3d reconstruction

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.883350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bab4a09d-6704-4e82-a92f-f57e48442c2c · outbound

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

Test3R: Learning to Reconstruct 3D at Test Time Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:06.934080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb21bbc6-ca08-41de-96b4-4abc845fd01f · outbound

This paper cites Learning by Transduction.

Test3R: Learning to Reconstruct 3D at Test Time Learning by Transduction

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:32:08.569013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b07c4ee8-fcd3-42a2-b244-fedf0abc59e2 · outbound

This paper cites Estimation of dependences based on empirical data.

Test3R: Learning to Reconstruct 3D at Test Time Estimation of dependences based on empirical data

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.382027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3655257e-41a2-4965-b359-cc1d1b589974 · outbound

This paper cites Large scale transductive svms.

Test3R: Learning to Reconstruct 3D at Test Time Large scale transductive svms

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.166722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d5f298-f514-4c48-8abd-26af199a63c8 · outbound

This paper cites Learning to classify text using support vector machines, volume 668.

Test3R: Learning to Reconstruct 3D at Test Time Learning to classify text using support vector machines, volume 668

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.217960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fcf264d-ad9f-4ece-ac5b-9c7d9b182164 · outbound

This paper cites Test-Time Training on Nearest Neighbors for Large Language Models.

Test3R: Learning to Reconstruct 3D at Test Time Test-Time Training on Nearest Neighbors for Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.253775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b445c651-9f90-42f3-a8b6-232f7b915113 · outbound

This paper cites Local learning algorithms.

Test3R: Learning to Reconstruct 3D at Test Time Local learning algorithms

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.356730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8f8c2048-8c73-4f13-8cf4-ceb0a09f93fd · outbound

This paper cites Svm-knn: Discriminative nearest neighbor classification for visual category recognition.

Test3R: Learning to Reconstruct 3D at Test Time Svm-knn: Discriminative nearest neighbor classification for visual category recognition

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.345355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ec6ea554-8aa4-4571-9c37-385b4a9bbc45 · outbound

This paper cites Test-time training with self-supervision for generalization under distribution shifts.

Test3R: Learning to Reconstruct 3D at Test Time Test-time training with self-supervision for generalization under distribution shifts

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.334869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6191a1ef-ce87-4cd1-8462-4548b21a191f · outbound

This paper cites Self-Supervised Policy Adaptation during Deployment.

Test3R: Learning to Reconstruct 3D at Test Time Self-Supervised Policy Adaptation during Deployment

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.450534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e098db-6306-45eb-939c-c1441895994e · outbound

This paper cites Online learning of unknown dynamics for model-based controllers in legged locomotion.

Test3R: Learning to Reconstruct 3D at Test Time Online learning of unknown dynamics for model-based controllers in legged locomotion

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.323905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d9a53a50-f2b9-425d-b70b-d0cee6130cf5 · outbound

This paper cites Ttt++: When does self-supervised test-time training fail or thrive? Advances in Neural Information Processing Systems, 34:21808–21820, 2021.

Test3R: Learning to Reconstruct 3D at Test Time Ttt++: When does self-supervised test-time training fail or thrive? Advances in Neural Information Processing Systems, 34:21808–21820, 2021

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.676630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc3b0edb-9c2d-4613-a898-39d8ab0b4578 · outbound

This paper cites Robust test-time adaptation in dynamic scenarios.

Test3R: Learning to Reconstruct 3D at Test Time Robust test-time adaptation in dynamic scenarios

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.303672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1f45e688-671e-4e8e-a34d-8ee3014f6ed1 · outbound

This paper cites Language Models are Few-Shot Learners.

Test3R: Learning to Reconstruct 3D at Test Time Language Models are Few-Shot Learners

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.881392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bd04bbc-e25c-4145-9091-421cd23b57d5 · outbound

This paper cites How can we know what language models know? Transactions of the Association for Computational Linguistics, 8:423–438, 2020.

Test3R: Learning to Reconstruct 3D at Test Time How can we know what language models know? Transactions of the Association for Computational Linguistics, 8:423–438, 2020

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:07.922310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a442b19-344c-4f3f-a1d9-23ee46068bcb · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

Test3R: Learning to Reconstruct 3D at Test Time AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.047299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34c15793-480f-4f0c-8171-0cc1c61ed8be · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Test3R: Learning to Reconstruct 3D at Test Time The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.118223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0df7c76-b8a0-4e50-b374-0fa7a111501a · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

Test3R: Learning to Reconstruct 3D at Test Time Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.190417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712e8857-7bed-48e4-a9ec-92e57aa3073c · outbound

This paper cites P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks.

Test3R: Learning to Reconstruct 3D at Test Time P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.307818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26312a19-e5ea-4353-b3ad-27598cfe3910 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

Test3R: Learning to Reconstruct 3D at Test Time An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.362346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37f8f84-b8a2-458b-8a1f-57deac6bdb48 · outbound

This paper cites Large-scale data for multiple-view stereopsis.

Test3R: Learning to Reconstruct 3D at Test Time Large-scale data for multiple-view stereopsis

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.386890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 188d8bd9-281a-45be-ac12-6ff250847423 · outbound

This paper cites A multi-view stereo benchmark with high-resolution images and multi- camera videos.

Test3R: Learning to Reconstruct 3D at Test Time A multi-view stereo benchmark with high-resolution images and multi- camera videos

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.247341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ed55fa40-a8ca-4ea1-936f-ddf1cd977a8b · outbound

This paper cites Visual Prompt Tuning for Test-time Domain Adaptation.

Test3R: Learning to Reconstruct 3D at Test Time Visual Prompt Tuning for Test-time Domain Adaptation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.393324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31b0d295-c038-42f8-a08a-eded372e8e7a · outbound

This paper cites Demon: Depth and motion network for learning monocular stereo.

Test3R: Learning to Reconstruct 3D at Test Time Demon: Depth and motion network for learning monocular stereo

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.169095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba02c823-0148-4038-b47a-6c42f662e34a · outbound

This paper cites DeepV2D: Video to Depth with Differentiable Structure from Motion.

Test3R: Learning to Reconstruct 3D at Test Time DeepV2D: Video to Depth with Differentiable Structure from Motion

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.399100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1559ea93-bd58-4d02-bc04-f14448fbe29c · outbound

This paper cites A benchmark and a baseline for robust multi-view depth estimation.

Test3R: Learning to Reconstruct 3D at Test Time A benchmark and a baseline for robust multi-view depth estimation

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.085491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 00eee936-5643-4764-9156-39cda516a1dd · outbound

This paper cites Vis-mvsnet: Visibility-aware multi-view stereo network.

Test3R: Learning to Reconstruct 3D at Test Time Vis-mvsnet: Visibility-aware multi-view stereo network

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.063411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 86e9c875-9c0f-4b2a-9610-1fbe37adfa00 · outbound

This paper cites Mvs2d: Efficient multi-view stereo via attention- driven 2d convolutions.

Test3R: Learning to Reconstruct 3D at Test Time Mvs2d: Efficient multi-view stereo via attention- driven 2d convolutions

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:09.023105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cf04d769-5d9b-4b1d-b0f4-9bfdc2fea161 · outbound

This paper cites Scene coordinate regression forests for camera relocalization in rgb-d images.

Test3R: Learning to Reconstruct 3D at Test Time Scene coordinate regression forests for camera relocalization in rgb-d images

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:32:08.878698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a5156f4d-9d00-4a77-a80e-e4365d54cb3d · outbound

This paper cites Neural rgb-d surface reconstruction.

Test3R: Learning to Reconstruct 3D at Test Time Neural rgb-d surface reconstruction

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.413988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f09dbfdd-dcfa-4843-9a4b-ffd141c0a897 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Test3R: Learning to Reconstruct 3D at Test Time Adam: A Method for Stochastic Optimization

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T00:32:08.417157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation f591ffa9-f648-49e2-90a6-30a3a2925c35 · inbound

Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT cites this paper.

Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGT Test3R: Learning to Reconstruct 3D at Test Time

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T18:23:09.928240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac5f74aa-9d9d-4083-a001-aae1379000d0 · inbound

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens cites this paper.

TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens Test3R: Learning to Reconstruct 3D at Test Time

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:20:11.285190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.