SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models | Paper Citation Record

Observation 406a59fe-1e26-4614-8284-1220506dbdf7 · outbound

This paper cites GPT-4 Technical Report.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.528694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3899654e-51cf-4047-8147-8fc65620184d · outbound

This paper cites SpaceLLaV A.https://huggingface.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models SpaceLLaV A.https://huggingface

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.715270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ef159a4d-37d4-4506-bfd3-d6e4a9577b20 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736,.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.537060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54101c4c-4803-4e16-8d9f-cd5527539fa6 · outbound

This paper cites Claude 3.5 Sonnet.https : / / www.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Claude 3.5 Sonnet.https : / / www

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.691472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d08d78bf-58cd-48f3-a510-6f425e17e097 · outbound

This paper cites Apollo syntheic dataset, 2019.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Apollo syntheic dataset, 2019

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.676342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1c09667c-7bfd-433e-beed-de79b75fe683 · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Scanqa: 3d question answering for spatial scene understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.662827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b680ca9b-60bc-408e-b398-2ded5eba2dc2 · outbound

This paper cites Qwen Technical Report.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Qwen Technical Report

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.553190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 210bf3bf-22e8-47c5-928b-c18b4892d11b · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.557935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 014d3939-6660-4473-93c9-d6dac68e29ea · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.563585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2379b6d3-b0e9-4702-8586-5485bee21225 · outbound

This paper cites ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.568854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcc0a7c-ab19-42be-8fca-2fcc0b0824dc · outbound

This paper cites Omni3D: A large benchmark and model for 3D object detection in the wild.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Omni3D: A large benchmark and model for 3D object detection in the wild

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.649771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f7518ae4-2fea-4820-9626-77596264aef2 · outbound

This paper cites nuscenes: A multi- modal dataset for autonomous driving.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models nuscenes: A multi- modal dataset for autonomous driving

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.634820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b3b2ee18-f9ae-4442-b275-15616a4374b7 · outbound

This paper cites Honeybee: Locality-enhanced projector for multimodal llm.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Honeybee: Locality-enhanced projector for multimodal llm

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.621016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6613005b-fd73-4555-b321-9c286ba2a0c4 · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Spatialvlm: Endow- ing vision-language models with spatial reasoning capabili- ties

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.586160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb75f2f4-66a5-4a0d-b871-a3b9d668f78a · outbound

This paper cites Vitamin: Designing scalable vision models in the vision-language era.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Vitamin: Designing scalable vision models in the vision-language era

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.598273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee237961-8d51-49cb-87d3-00b205a249fb · outbound

This paper cites SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.594324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7428130-25d9-401f-b0f8-ff71c63dfd4e · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Imagenet: A large-scale hierarchical image database

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.584277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2fe4363-1272-494e-bdbc-866bceb42454 · outbound

This paper cites The Llama 3 Herd of Models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.602876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f4a9e3c-3739-4cf3-b85d-a0bcc6ded7c3 · outbound

This paper cites Prob- ing the 3d awareness of visual foundation models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Prob- ing the 3d awareness of visual foundation models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.571158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 01858a9a-0c1a-4c10-9b5b-b5316d65ceee · outbound

This paper cites DataComp: In search of the next generation of multimodal datasets.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models DataComp: In search of the next generation of multimodal datasets

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.611469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf252cec-806e-40cb-bddd-14c085680d2c · outbound

This paper cites Are we ready for autonomous driving? the kitti vision benchmark suite.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Are we ready for autonomous driving? the kitti vision benchmark suite

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.558228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 963710cf-9f38-43ac-9697-a4faa7d1eb9a · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.619809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5853c801-4a09-4244-a610-be3722600d4d · outbound

This paper cites Masked autoencoders are scalable vision learners.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Masked autoencoders are scalable vision learners

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.535650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0bb241a8-9b5a-49e6-a74c-b4964909fd04 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.628147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab3e944d-9ffc-41be-8881-0afa42753c6a · outbound

This paper cites Open- clip, 2021.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Open- clip, 2021

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.632345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efad3a13-2355-4f59-857a-bcf21ed9e00d · outbound

This paper cites Novum: Neural object volumes for robust object classification.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Novum: Neural object volumes for robust object classification

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.636714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a18a1e3-b8c5-4f12-919f-d9372cfeb9b4 · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Scaling up visual and vision-language representation learning with noisy text supervision

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.641122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b70a587-e6b4-442f-a52b-039d3219ebb4 · outbound

This paper cites Mistral 7B.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Mistral 7B

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.645314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23def1e4-6e16-456d-a272-19374143cbe0 · outbound

This paper cites Perspective fields for single image cam- era calibration.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Perspective fields for single image cam- era calibration

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.496761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0f29b4b2-cd60-4d8a-bccf-fe8980c20c1c · outbound

This paper cites Segment Anything.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Segment Anything

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.654030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6ad7280-ab4e-4084-8836-82d3c4087e82 · outbound

This paper cites Segment any- thing.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Segment any- thing

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.482808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e8503dba-ab6d-41a7-ba90-27a7802de402 · outbound

This paper cites Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123:32–73, 2017.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Visual genome: Connecting language and vision using crowdsourced dense image annotations.International journal of computer vision, 123:32–73, 2017

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.468752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6133f4d5-e8dc-43b8-b982-5d7bc1ba9234 · outbound

This paper cites an unresolved cited work.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-16T04:40:28.455596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ec3d869b-35a5-4bf8-a173-9680cbc1cfd0 · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.668620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da067013-52b3-4923-b835-b331d5dff1cf · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.672593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a9eeaed-3940-4f5e-bf21-6cac2194feff · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.676116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e191db48-ad61-4223-9dab-3e802c457a8f · outbound

This paper cites What If We Recaption Billions of Web Images with LLaMA-3?.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models What If We Recaption Billions of Web Images with LLaMA-3?

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.679528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d8537d9-59b3-4597-bf88-eb1310a983ab · outbound

This paper cites Learning customized visual models with retrieval-augmented knowledge.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Learning customized visual models with retrieval-augmented knowledge

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.424103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b5370f09-d4d9-4e65-823c-dd477f4ebdd9 · outbound

This paper cites Improved baselines with visual instruction tuning.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Improved baselines with visual instruction tuning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.411147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8563a318-bdce-4f59-94e2-8c66228b8f8b · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.692491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9078385e-9047-431d-88a5-8539b76bdac5 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36, 2024.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Visual instruction tuning.Advances in neural information processing systems, 36, 2024

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.389689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d40ee3a-6590-4210-971b-7cb5e430e012 · outbound

This paper cites Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.701110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b4f0ab1-d640-46cc-b582-d973fb3af87f · outbound

This paper cites DeepSeek-VL: Towards Real-World Vision-Language Understanding.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models DeepSeek-VL: Towards Real-World Vision-Language Understanding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.706213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d41879e-6ea7-45c5-9dd6-5fb92975967a · outbound

This paper cites Robust category-level 6d pose estimation with coarse-to-fine rendering of neural features.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Robust category-level 6d pose estimation with coarse-to-fine rendering of neural features

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.710906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb3e3658-1c82-496c-8a94-595420f171ad · outbound

This paper cites Imagenet3d: Towards general-purpose object-level 3d understanding.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Imagenet3d: Towards general-purpose object-level 3d understanding

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.367631Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ee39a5d8-b409-4f20-afb8-66877bafd94d · outbound

This paper cites MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.719431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f212ba-c183-4ba0-ac22-e03927a53aff · outbound

This paper cites Dinov2: Learning robust visual features without supervision.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Dinov2: Learning robust visual features without supervision

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.353857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 46c97bf3-ed26-462e-8532-8f29b56a2c81 · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Learn- ing transferable visual models from natural language super- vision

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.340434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ab98a02a-21ff-4a25-aa69-358024560e93 · outbound

This paper cites GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.732388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ce633a1-7150-4fe4-b5d2-0c05685ba58f · outbound

This paper cites Susskind.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Susskind

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.737271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0480b152-9d4f-456f-8a1f-4cf1911f0bd2 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models High-resolution image synthesis with latent diffusion models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.742087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 006893b9-ae58-480a-858a-34eae99b0e66 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in Neural In- formation Processing Systems, 35:25278–25294, 2022.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in Neural In- formation Processing Systems, 35:25278–25294, 2022

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.746271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9eed4e5-c451-414b-9f1c-d369abc0d3cf · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.750251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38d7f83c-8884-48a2-a43a-5028083c44e9 · outbound

This paper cites Sun rgb-d: A rgb-d scene understanding benchmark suite.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Sun rgb-d: A rgb-d scene understanding benchmark suite

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.292913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5079e0ca-85ec-40d6-8dd8-fc7220e45669 · outbound

This paper cites Core knowl- edge.Developmental science, 10(1):89–96, 2007.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Core knowl- edge.Developmental science, 10(1):89–96, 2007

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.279345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2d34e57a-31d7-4600-b65c-438238908d63 · outbound

This paper cites Revisiting unreasonable effectiveness of data in deep learning era.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Revisiting unreasonable effectiveness of data in deep learning era

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.266026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 136a0093-736c-4ee3-81e0-c392bb18cacf · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Gemini: A Family of Highly Capable Multimodal Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.766525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7432001d-b856-4980-8200-07a6a7a57b7b · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.770707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58112f68-ab1b-4fd0-9de8-9a674ab0493b · outbound

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

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.775308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cb36f74-af69-48b2-b64b-007267717ddc · outbound

This paper cites 3d-aware visual question answering about parts, poses and occlusions.Advances in Neural Information Processing Systems, 36, 2024.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models 3d-aware visual question answering about parts, poses and occlusions.Advances in Neural Information Processing Systems, 36, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.252560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 87ad28bf-6065-4e22-a3aa-3ad93f02c52b · outbound

This paper cites Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.782481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9413468e-6207-41cb-a66c-0ba8a4f1ed2b · outbound

This paper cites Depth anything: Unleashing the power of large-scale unlabeled data.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Depth anything: Unleashing the power of large-scale unlabeled data

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.786283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bcdd412-64c8-4b6c-bae0-b479654111c3 · outbound

This paper cites Depth anything: Unleashing the power of large-scale unlabeled data.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Depth anything: Unleashing the power of large-scale unlabeled data

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.789631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641aa501-4832-4c54-a095-8c145200b324 · outbound

This paper cites 3D Question Answering.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models 3D Question Answering

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.793012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a28dadf-2403-4a41-b966-8c54e4654bec · outbound

This paper cites CoCa: Contrastive Captioners are Image-Text Foundation Models.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models CoCa: Contrastive Captioners are Image-Text Foundation Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.796715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0976f13-42b8-4a8e-b0c9-79e2abede03f · outbound

This paper cites Recognize Anything: A Strong Image Tagging Model.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Recognize Anything: A Strong Image Tagging Model

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.800978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05828b61-7e53-4419-969c-22fdbc6382e6 · outbound

This paper cites Recognize anything: A strong image tagging model.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Recognize anything: A strong image tagging model

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.222985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c6ea85e2-6324-4c84-89cb-3e5cc5a09a3b · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.210551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3a2932da-f0a4-413f-a27c-6f50635ac041 · outbound

This paper cites iBOT: Image BERT Pre-Training with Online Tokenizer.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models iBOT: Image BERT Pre-Training with Online Tokenizer

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T04:40:27.814069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40f19090-a735-4d0d-a78f-2b57a9580da8 · outbound

This paper cites yes” as the answer and 120 questions have “no.

SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models yes” as the answer and 120 questions have “no

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T04:40:28.195914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers