Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence | Paper Citation Record

Observation fa0b5756-bf2b-4847-b447-c273aaa2b0fa · outbound

This paper cites Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-12T00:42:00.507497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a75c6b97-646a-4e0f-b568-05e7bc57cf1d · outbound

This paper cites Mmsi-bench: A benchmark for multi-image spatial intelligence,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Mmsi-bench: A benchmark for multi-image spatial intelligence,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.067973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 34a4db5b-51df-4362-ad64-75b660f37e62 · outbound

This paper cites Reltr: Relation transformer for scene graph generation,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Reltr: Relation transformer for scene graph generation,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.056242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0a4b415d-339e-4ee6-be25-7c74817856bf · outbound

This paper cites Scenehgn: Hierarchical graph networks for 3d indoor scene generation with fine-grained geometry,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Scenehgn: Hierarchical graph networks for 3d indoor scene generation with fine-grained geometry,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.044667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 9bcfd0be-b146-43e3-b7da-60c8c8c405d0 · outbound

This paper cites Planner3d: Llm-enhanced graph prior meets 3d indoor scene explicit regularization,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Planner3d: Llm-enhanced graph prior meets 3d indoor scene explicit regularization,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.033442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e3bf02de-6c1f-4c36-8583-73521a0c6f53 · outbound

This paper cites Knowledge-based embodied question answering,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Knowledge-based embodied question answering,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.021322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2efd8b0f-15b2-43f6-98ff-8c9bfe855a4a · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence 3d- llava: Towards generalist 3d lmms with omni superpoint transformer,

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:01.008126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ac4b85b8-710c-41c4-b220-e7a701b1c2f8 · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Chat-scene: Bridging 3d scene and large language models with object identifiers,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.994770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 56723bf1-f0ab-442c-b22c-14e0e362c680 · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Ll3da: Visual interactive instruction tuning for omni-3d understanding reasoning and planning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.977188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 084ee99f-87f7-4404-987d-3bd98380aab5 · outbound

This paper cites Matrix3d: Large photogrammetry model all-in-one,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Matrix3d: Large photogrammetry model all-in-one,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.964772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a8dfecff-48ee-471b-8b69-c4c0bc1b4ad1 · outbound

This paper cites WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.736108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d338d57-8bf8-4b29-88c6-fc0fd8d9ad4c · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Llava-3d: A simple yet effective pathway to empowering lmms with 3d capabilities,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.951990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6a355eb7-1502-4d17-9fdd-bd854e7f46ae · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Video-3d llm: Learning position- aware video representation for 3d scene understanding,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.939410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f3cb7d44-5057-4606-a2e2-e41e8ad24b36 · outbound

This paper cites Sti-bench: Are mllms ready for precise spatial-temporal world understanding?.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Sti-bench: Are mllms ready for precise spatial-temporal world understanding?

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.926336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c75607ef-8626-4f81-8927-24d0338f5caf · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Thinking in space: How multimodal large language models see, remember, and recall spaces,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.754474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b1202d0-ddab-4dc3-a216-f4aafedf137c · outbound

This paper cites Spacemind: Camera-guided modality fusion for spatial reasoning in vision-language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Spacemind: Camera-guided modality fusion for spatial reasoning in vision-language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.758432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69cf5398-d942-44a2-bdc2-73d22ae0e4bc · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Learning from videos for 3d world: Enhancing mllms with 3d vision geometry priors,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.899765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 44abb8d1-e15c-4ec2-8da0-aa7eeb66ab65 · outbound

This paper cites Spatial-mllm: Boosting mllm capabilities in visual-based spatial intelligence,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Spatial-mllm: Boosting mllm capabilities in visual-based spatial intelligence,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.885051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 92b67692-c6a9-487a-ba77-965b77b5caf6 · outbound

This paper cites S 3-TIR: Coupled spatial-spectral splatting for thermal infrared novel view synthesis,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence S 3-TIR: Coupled spatial-spectral splatting for thermal infrared novel view synthesis,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.872355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5b69ced3-2306-4dfb-a4ff-4c4c5bfc560f · outbound

This paper cites Uncertainty-aware medical diagnostic phrase identification and grounding,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Uncertainty-aware medical diagnostic phrase identification and grounding,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.859655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 465ab7ff-8382-4041-a5b7-0c43e2ebd630 · outbound

This paper cites Inter-task weaving in image enhancement: From a new unified architecture to a better meta-representation learning,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Inter-task weaving in image enhancement: From a new unified architecture to a better meta-representation learning,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.847350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ad2ae15c-8a41-420f-b65a-6e40c2e076bc · outbound

This paper cites World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-12T00:42:00.395525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 08cfe3d2-841a-4f35-b784-d0df31110469 · outbound

This paper cites From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-12T00:42:00.376185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 102fcf12-9f13-4b14-b0c9-9b7d70dc3f16 · outbound

This paper cites Striving for faster and better: A one-layer architecture with auto re-parameterization for low- light image enhancement,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Striving for faster and better: A one-layer architecture with auto re-parameterization for low- light image enhancement,

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.833576Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b40b98aa-a499-49c5-b824-ad152e0bce24 · outbound

This paper cites Sentence-level prompts benefit composed image retrieval,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Sentence-level prompts benefit composed image retrieval,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.820268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c1714e56-c16c-4b41-8862-d4b281b745c5 · outbound

This paper cites Biprolora: Bilevel prompt lora for real scene recovery,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Biprolora: Bilevel prompt lora for real scene recovery,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.798698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 981f363c-b46f-40cb-8db3-437b42c65725 · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.803830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c67ad0c-57b4-49e5-b551-8ede166d501f · outbound

This paper cites Causalspatial: A benchmark for object-centric causal spatial reasoning,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Causalspatial: A benchmark for object-centric causal spatial reasoning,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.808519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd110462-3946-4c10-b241-6a8d093c6b9f · outbound

This paper cites Person re-identification method based on color attack and joint defence,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Person re-identification method based on color attack and joint defence,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.785534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0c6f9aa4-b172-421b-b20c-68995828f0c6 · outbound

This paper cites A theory-inspired framework for few-shot cross-modal sketch person re-identification,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence A theory-inspired framework for few-shot cross-modal sketch person re-identification,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.769165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 67f2cf68-55dc-4f0d-9b2a-3168b29f9cfd · outbound

This paper cites 3d-llm: Injecting the 3d world into large language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence 3d-llm: Injecting the 3d world into large language models,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.754784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1c91139e-4af7-4b9e-bcbc-82c866b61e7d · outbound

This paper cites Pointllm: Empowering large language models to understand point clouds,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Pointllm: Empowering large language models to understand point clouds,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.741999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 0f74b3ed-ca82-47a3-91eb-dbaeedc78218 · outbound

This paper cites Jm3d & jm3d-llm: Elevating 3d representation with joint multi-modal cues,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Jm3d & jm3d-llm: Elevating 3d representation with joint multi-modal cues,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.729632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 14b0cd5f-1202-4a8d-a338-d4f31edc076e · outbound

This paper cites Chat-scene++: Exploiting context-rich object identification for 3d llm,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Chat-scene++: Exploiting context-rich object identification for 3d llm,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.715217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6d0c30a8-05bb-4042-8821-db0fcff04f78 · outbound

This paper cites Think with 3d: Geometric imagination grounded spatial reasoning from limited views,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Think with 3d: Geometric imagination grounded spatial reasoning from limited views,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.700453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a7407fb1-1f6b-4b4e-ba7b-44eda89cc92d · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Chain-of-thought prompting elicits reasoning in large language models,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.839836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e28b4d-8053-4958-8b1d-5381aad051ff · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Tree of thoughts: Deliberate problem solving with large language models,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.678142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8065cc08-7913-4038-9279-8d69d8aa2863 · outbound

This paper cites Graph of thoughts: Solving elaborate problems with large language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Graph of thoughts: Solving elaborate problems with large language models,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.664577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 2c4b291a-a7ed-4a9a-86e1-ae4a0200e764 · outbound

This paper cites Let’s verify step by step,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Let’s verify step by step,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.649620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation b751b9f6-ffaa-4b52-b946-18baf4a1a523 · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Math-shepherd: Verify and reinforce llms step-by-step without human annotations,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.854460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4da5560-b086-4d1b-8d3d-95f87956128f · outbound

This paper cites Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.858335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb79a1d-bff9-4f96-9f0c-794ef291d4f3 · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Scannet: Richly-annotated 3d reconstructions of indoor scenes,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.862512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3cfe6e-9049-4eef-a162-122f9b1fef6c · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Scannet++: A high- fidelity dataset of 3d indoor scenes,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.622085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f2ea5f16-2b7c-4fda-84b5-04cddde9d17b · outbound

This paper cites Matterport3d: Learning from rgb-d data in indoor environments,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Matterport3d: Learning from rgb-d data in indoor environments,

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.607924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation eb0b887d-a36f-4cb0-aa75-7b3ac0c649dd · outbound

This paper cites Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Habitat-matterport 3d dataset (hm3d): 1000 large-scale 3d environments for embodied ai,

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.593345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 44e41d85-4cdc-4484-8f6b-dd3f553a06bf · outbound

This paper cites Qwen3-VL Technical Report.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Qwen3-VL Technical Report

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.877286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f826c4-63a9-46a0-9a8c-e12b286ba705 · outbound

This paper cites Xiaomi mimo-vl-miloco technical report,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Xiaomi mimo-vl-miloco technical report,

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.881477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d57115f8-f256-4b4f-b79c-2f078e149ce1 · outbound

This paper cites The Llama 3 Herd of Models.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence The Llama 3 Herd of Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.885463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b508e40f-587d-41ed-bb44-718a51675401 · outbound

This paper cites Llava-cot: Let vision language models reason step-by-step,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Llava-cot: Let vision language models reason step-by-step,

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.578690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d3e23f11-305a-4ae4-afd3-429acccaa405 · outbound

This paper cites Kimi-VL Technical Report.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Kimi-VL Technical Report

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.894517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5a3ff73-3193-4835-9725-db3652106290 · outbound

This paper cites DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.899545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2947eef5-fb95-4477-8f1e-9ffb1c9b5b3c · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence LLaVA-Video: Video Instruction Tuning With Synthetic Data

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.905547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42b028b7-aa18-4b0a-a3fc-a9e45e517213 · outbound

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

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.910894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 051d18e8-95b8-417a-8675-21220c70e369 · outbound

This paper cites Spatialvlm: Endowing vision-language models with spatial reasoning capabilities,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Spatialvlm: Endowing vision-language models with spatial reasoning capabilities,

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.565575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6c907c9e-a257-4a37-a42c-479b043d0384 · outbound

This paper cites SpaceR: Reinforcing MLLMs in Video Spatial Reasoning.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence SpaceR: Reinforcing MLLMs in Video Spatial Reasoning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.923751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d193410-6ae2-43c6-8354-05ccb707cc67 · outbound

This paper cites Scaling spatial intelligence with multimodal foundation models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Scaling spatial intelligence with multimodal foundation models,

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.553165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 66201e29-81c8-4fd0-9102-98902c7ea922 · outbound

This paper cites Visual spatial tuning,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Visual spatial tuning,

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.932722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c05ed17-c5b4-4dd5-813f-46494c4c1631 · outbound

This paper cites OpenAI GPT-5 System Card.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence OpenAI GPT-5 System Card

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-12T00:41:59.936578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e3502e0-3f8a-462c-a8d6-f5d7c63dfe4c · outbound

This paper cites Gemini 3.1 pro: Model card,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Gemini 3.1 pro: Model card,

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.541699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ff22761d-01d1-44fa-98fb-dc588265d3ab · outbound

This paper cites Self-consistency improves chain of thought reasoning in language models,.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence Self-consistency improves chain of thought reasoning in language models,

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.530332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fcc6012a-dc49-46d6-8438-44ba128cb92b · outbound

This paper cites He is currently a Professor at the Suzhou Institute for Advanced Research/School of Mathematical Sciences at the University of Science and Technology of China.

Advantage-Guided Gate: Reshaping Open-Ended Reasoning for Vision-Based Spatial Intelligence He is currently a Professor at the Suzhou Institute for Advanced Research/School of Mathematical Sciences at the University of Science and Technology of China

Reference 2010

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T00:42:00.519413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers