Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching | Paper Citation Record

Observation 6ae4d19d-96f5-4256-b781-81c3a4e02458 · outbound

This paper cites Qwen3-VL Technical Report.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Qwen3-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.073648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1dd6f1b6-e6fe-47e5-9ccf-1113c2729634 · outbound

This paper cites Qwen2.5-vl technical report, 2025.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Qwen2.5-vl technical report, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89364235-0444-4515-8ee0-27aaf8e1c766 · outbound

This paper cites Hot3d: Hand and object tracking in 3d from egocentric multi-view videos.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Hot3d: Hand and object tracking in 3d from egocentric multi-view videos

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0813fcfc-354e-457d-b509-a2387b0d01c6 · outbound

This paper cites Graph-cut ransac.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Graph-cut ransac

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eee1b83d-cb4c-4b6e-a8e0-51f5e45fa590 · outbound

This paper cites Magsac: marginalizing sample consensus.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Magsac: marginalizing sample consensus

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a30c06-a3af-4a02-ab5a-95bffb1f5cee · outbound

This paper cites Surf: Speeded up robust features.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Surf: Speeded up robust features

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e44bacd5-5e46-41ba-9e82-6a274be1912b · outbound

This paper cites Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.111959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a6f9749d-9730-47c1-b5c4-d20f0c48171c · outbound

This paper cites Assignment problems: revised reprint.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Assignment problems: revised reprint

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1ccb55f-fade-44c5-a941-4f5298ab4061 · outbound

This paper cites SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.141917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 705572a1-80de-4b2a-b8c0-5aee124588c2 · outbound

This paper cites Are we on the right way for evaluating large vision-language models?Advances in Neural Informa- tion Processing Systems, 37:27056–27087, 2024.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Are we on the right way for evaluating large vision-language models?Advances in Neural Informa- tion Processing Systems, 37:27056–27087, 2024

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa49c86-523a-47ed-90ed-71d5b80d8d96 · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.084858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a01720ff-a0bd-4111-bf13-23da3c5b1999 · outbound

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

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Scannet: Richly-annotated 3d reconstructions of indoor scenes

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63ef0228-c17b-4df3-8f59-d5de49d22778 · outbound

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

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Superpoint: Self-supervised interest point detection and description

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77cc1285-2155-41fa-9d5e-fe6602069f07 · outbound

This paper cites Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.097894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e7a02385-b46b-42b8-ac01-8abcbc39fb28 · outbound

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

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching D2-net: A trainable cnn for joint detection and description of local features

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0722f048-ecc0-4eba-840d-a46b94ed7f30 · outbound

This paper cites Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography.Communications of the ACM, 24(6):381–395, 1981.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography.Communications of the ACM, 24(6):381–395, 1981

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d928d06-39c7-4997-89f6-e414c19740b3 · outbound

This paper cites A graduated assignment algorithm for graph matching.IEEE Transactions on pattern analysis and machine intelligence, 18(4):377–388, 2002.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching A graduated assignment algorithm for graph matching.IEEE Transactions on pattern analysis and machine intelligence, 18(4):377–388, 2002

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7757d196-dabc-4a43-a121-62e6d5dbe551 · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633– 638, 2025.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633– 638, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb58b551-ce95-4bd7-8481-5b8e60218292 · outbound

This paper cites Projective reconstruction and invariants from multiple images.IEEE Transactions on Pattern Analy- sis and Machine Intelligence, 16(10):1036–1041, 1994.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Projective reconstruction and invariants from multiple images.IEEE Transactions on Pattern Analy- sis and Machine Intelligence, 16(10):1036–1041, 1994

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401c8c08-c5ba-4db5-afb7-0b9f285f3002 · outbound

This paper cites Metric3d v2: A versatile monocular geomet- ric foundation model for zero-shot metric depth and surface normal estimation.IEEE TPAMI, 2024.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Metric3d v2: A versatile monocular geomet- ric foundation model for zero-shot metric depth and surface normal estimation.IEEE TPAMI, 2024

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 026976d1-559f-4146-a53f-a64a23478789 · outbound

This paper cites NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.129942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1954a7c0-0776-4997-9ddc-a72de2a85f7f · outbound

This paper cites RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching RoboBrain: A Unified Brain Model for Robotic Manipulation from Abstract to Concrete

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.070919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ddfa18ac-5c9e-4185-934d-a56d26e986bc · outbound

This paper cites Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Omnispatial: Towards comprehensive spatial reasoning benchmark for vision language models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.076549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 642fa5f6-ee6a-487c-8480-dda05b518f07 · outbound

This paper cites Image Matching across Wide Baselines: From Paper to Practice.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Image Matching across Wide Baselines: From Paper to Practice

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.079352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9628a8c-e701-4de6-af9f-848344b9c5b5 · outbound

This paper cites Segment any- thing.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Segment any- thing

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98f32c98-ebb9-4537-ab21-6110ca5c192a · outbound

This paper cites Building and better understanding vision- language models: Insights and future directions.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Building and better understanding vision- language models: Insights and future directions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5485ff7a-a715-453b-91e4-b0e02c70a3fe · outbound

This paper cites Dl3dv-10k: A large-scale scene dataset for deep learning-based 3d vision.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Dl3dv-10k: A large-scale scene dataset for deep learning-based 3d vision

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18bf7330-5e3a-4580-80fb-41f7438dcda9 · outbound

This paper cites Improved baselines with visual instruction tuning.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Improved baselines with visual instruction tuning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f18e4c8c-ca52-4718-bf4d-3d50251454ed · outbound

This paper cites Zhang, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, and David Novotny.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Zhang, Natalia Neverova, Andrea Vedaldi, Roman Shapovalov, and David Novotny

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99dd230c-41ca-493d-b93b-3c4b252498d2 · outbound

This paper cites Decoupled Weight Decay Regularization.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Decoupled Weight Decay Regularization

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.132415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bb3d0ad6-5e7a-4760-9381-041ac7f3081d · outbound

This paper cites Distinctive image features from scale- invariant keypoints.International journal of computer vi- sion, 60(2):91–110, 2004.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Distinctive image features from scale- invariant keypoints.International journal of computer vi- sion, 60(2):91–110, 2004

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f067a1f9-4463-4d8a-ac2c-ab2324be276d · outbound

This paper cites 3dsrbench: A comprehensive 3d spatial reasoning benchmark.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching 3dsrbench: A comprehensive 3d spatial reasoning benchmark

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da8823c-ec06-40dc-ab08-1ad93192093b · outbound

This paper cites Working hard to know your neighbor’s mar- gins: Local descriptor learning loss.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Working hard to know your neighbor’s mar- gins: Local descriptor learning loss

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34f60a06-49f0-4d99-8083-1ca572070ed0 · outbound

This paper cites GPT-4 Technical Report.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching GPT-4 Technical Report

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.122127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 14e5a29d-44af-473e-891f-14b87e8ecdef · outbound

This paper cites Hello gpt-4o.OpenAI Blog, 2024.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Hello gpt-4o.OpenAI Blog, 2024

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d48be2-94b0-4323-9ee4-e0545ddd7090 · outbound

This paper cites Manivideo: Generating hand-object manipulation video with dexterous and generalizable grasping.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Manivideo: Generating hand-object manipulation video with dexterous and generalizable grasping

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0820559-58e6-425a-9fe4-bb31a18f40bd · outbound

This paper cites Wide baseline stereo matching.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Wide baseline stereo matching

Reference 37

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d011b345-3398-475d-b9ab-fe9955d2186b · outbound

This paper cites Sat: Spa- tial aptitude training for multimodal language models.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Sat: Spa- tial aptitude training for multimodal language models

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T02:36:27.124633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 496f5e75-c002-42fa-8b79-0ce887b55b4f · outbound

This paper cites Com- mon objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Com- mon objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction

Reference 39

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b3afa1c-4231-4cf3-957e-ea354cfcd599 · outbound

This paper cites R2D2: Repeatable and Reliable Detector and Descriptor.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching R2D2: Repeatable and Reliable Detector and Descriptor

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.112698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bd27d2d4-6512-48e6-b00a-63197ea4a73f · outbound

This paper cites Orb: An efficient alternative to sift or surf.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Orb: An efficient alternative to sift or surf

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab807407-ee27-4dbd-914f-2bb57f1c882b · outbound

This paper cites PhD thesis, INRIA, 1995.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching PhD thesis, INRIA, 1995

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5744ddd-cfb1-4fe1-adad-be546c13c85f · outbound

This paper cites Structure- from-motion revisited.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Structure- from-motion revisited

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 312c2b02-444a-400b-b41a-3549b832ddb6 · outbound

This paper cites Robospatial: Teaching spatial understanding to 2d and 3d vision-language models for robotics.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Robospatial: Teaching spatial understanding to 2d and 3d vision-language models for robotics

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba3719b2-0304-4446-a01f-f0336982a128 · outbound

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

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Gemini: A Family of Highly Capable Multimodal Models

Reference 45

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T02:36:27.118161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f9cc5f5f-bdb1-4b91-a9c8-5fdde233f377 · outbound

This paper cites Sosnet: Second order similarity reg- ularization for local descriptor learning.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Sosnet: Second order similarity reg- ularization for local descriptor learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af5fd0af-da59-447c-8ac7-9698c2996a0b · outbound

This paper cites Vggt: Vi- sual geometry grounded transformer.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Vggt: Vi- sual geometry grounded transformer

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0368829d-6d55-416b-9f5a-7e427061e7e6 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.120626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5654e44d-c9f7-4a85-8f9f-86b073678946 · outbound

This paper cites Moge: Unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Moge: Unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c1a49a8-7ee5-4981-986b-325be80844d1 · outbound

This paper cites Site: towards spatial intelligence thorough evaluation.arXiv preprint arXiv:2505.05456,.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Site: towards spatial intelligence thorough evaluation.arXiv preprint arXiv:2505.05456,

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.127268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e4db9203-f400-4198-ba53-7fb855936f39 · outbound

This paper cites Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.134981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cca67599-480f-462f-8ab7-ef016ee9b372 · outbound

This paper cites V?: Guided visual search as a core mechanism in multimodal llms.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching V?: Guided visual search as a core mechanism in multimodal llms

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eca3dc7-f60e-4af2-8538-1d3eb5a1c9ea · outbound

This paper cites Realworldqa: Real-world visual question answering benchmark.https://x.ai/news/grok-1.5v, 2024.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Realworldqa: Real-world visual question answering benchmark.https://x.ai/news/grok-1.5v, 2024

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 799da79a-0794-4675-b979-ba254ab09e3c · outbound

This paper cites Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.138259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f1317aff-d042-47fd-a45f-484f16b20782 · outbound

This paper cites Thinking in space: How mul- timodal large language models see, remember, and recall spaces.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Thinking in space: How mul- timodal large language models see, remember, and recall spaces

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1804b6-e976-403b-b10d-efdc7dd932ac · outbound

This paper cites Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.114650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3abb23f5-eb12-4e73-9339-8c2afe4e338e · outbound

This paper cites Spa- tial mental modeling from limited views.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Spa- tial mental modeling from limited views

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.109497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cafdc826-d6d9-48dd-ad2e-719f58afb9cb · outbound

This paper cites Lmms- eval: Reality check on the evaluation of large multimodal models, 2024.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Lmms- eval: Reality check on the evaluation of large multimodal models, 2024

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d39ebf-6efe-4444-ae15-8c6ff73527a1 · outbound

This paper cites Long Context Transfer from Language to Vision.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Long Context Transfer from Language to Vision

Reference 59

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.103532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ab7348e-9927-4180-ab56-fee3d6ea73df · outbound

This paper cites MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.094847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 59631231-82f1-48ef-91b3-68a6c3106ccb · outbound

This paper cites Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.106597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7de3e548-9bd1-463c-9c85-c1f7e271e6a2 · outbound

This paper cites RoboRefer: Towards spatial referring with rea- soning in vision-language models for robotics.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching RoboRefer: Towards spatial referring with rea- soning in vision-language models for robotics

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:27.091415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b2c6241f-bb69-42d8-bf3e-1dfea16b0a79 · outbound

This paper cites Stereo magnification: learning view synthesis using multiplane images.ACM Transactions on Graphics (TOG), 37(4):1–12, 2018.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Stereo magnification: learning view synthesis using multiplane images.ACM Transactions on Graphics (TOG), 37(4):1–12, 2018

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5418be54-f9b9-48a6-8f34-7ddef12584e9 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.090117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 44fc81a2-c9dd-4d62-b898-e68c27f24fca · outbound

This paper cites Sega- gent: Exploring pixel understanding capabilities in mllms by imitating human annotator trajectories.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Sega- gent: Exploring pixel understanding capabilities in mllms by imitating human annotator trajectories

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f9fb93-a9d2-48ee-a297-28f0690b62cd · outbound

This paper cites ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning

Reference 66

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:36:27.100708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1750721d-d4f7-405a-8af5-46f9d6fc334d · outbound

This paper cites 7 – Implementation Details:Complete specifi- cations of data generation pipeline, experimental setup, prompt template, and curriculum progression schedules.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching 7 – Implementation Details:Complete specifi- cations of data generation pipeline, experimental setup, prompt template, and curriculum progression schedules

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb318602-0cdf-4692-8b4a-01ddb380f6b1 · outbound

This paper cites an unresolved cited work.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Unresolved cited work

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6132f501-f417-4ee5-9729-7154c0949599 · outbound

This paper cites Supervised Fine-tuning.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching Supervised Fine-tuning

Reference 69

Resolution: malformed identifier; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7103c3-9d8d-46d9-9624-e453095fb1d1 · outbound

This paper cites None” (F5).ReasonMatch-Bench includes regions that legitimately have no correspondence in the other view. F5 measures whether the model uses the “none.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching None” (F5).ReasonMatch-Bench includes regions that legitimately have no correspondence in the other view. F5 measures whether the model uses the “none

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4e87068-946b-4661-84d3-50b28635c487 · outbound

This paper cites 1": "1",.

Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching 1": "1",

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-28T10:48:24.523702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers