Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation | Paper Citation Record

Observation 87102886-f169-4b84-a307-920d8b8cf547 · outbound

This paper cites Vqa: Visual question answering.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Vqa: Visual question answering

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.673764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1baaa2c-29cd-459b-8cd8-0bd917856433 · outbound

This paper cites Qwen2.5-VL Technical Report.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Qwen2.5-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.709112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6563afa-6cfa-45d2-b7a5-fa893b1a44db · outbound

This paper cites Where did i leave my keys?- episodic-memory-based question answering on egocentric videos.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Where did i leave my keys?- episodic-memory-based question answering on egocentric videos

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.760465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5afb2f-81d0-4d25-bcfd-99e37fb528cc · outbound

This paper cites Ad- abins: Depth estimation using adaptive bins.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Ad- abins: Depth estimation using adaptive bins

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.813459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53c3138e-a0d3-48de-b8b1-ae1269a4eec2 · outbound

This paper cites Local- bins: Improving depth estimation by learning local distributions.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Local- bins: Improving depth estimation by learning local distributions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.889620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c913e4c3-f841-42a2-a44e-5bb888d908cd · outbound

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

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:14.973132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b00dd320-b97d-4d9c-b48c-de6115cbe39c · outbound

This paper cites Scene text visual question answering.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Scene text visual question answering

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.051371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0904920c-fad8-4d7d-861f-109b43a2e7b4 · outbound

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

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.110105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb49d6b0-ea75-4ba5-ad42-13c9129251b5 · outbound

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

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.160109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edc05bd7-0390-45f0-82c1-7042fad95dfe · outbound

This paper cites VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation VidEgoThink: Assessing Egocentric Video Understanding Capabilities for Embodied AI

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.211777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e551c8d-b69d-4ceb-a583-a5fa3b571b01 · outbound

This paper cites Egothink: Evaluating first-person per- spective thinking capability of vision-language models.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egothink: Evaluating first-person per- spective thinking capability of vision-language models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.261373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7200e93a-5def-46fe-bcb1-3cace70790b4 · outbound

This paper cites In- structblip: Towards general-purpose vision-language models with in- struction tuning.Advances in neural information processing systems, 36:49250–49267, 2023.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation In- structblip: Towards general-purpose vision-language models with in- struction tuning.Advances in neural information processing systems, 36:49250–49267, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.307319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6fbf91-1078-4122-86ee-f7e220cad36c · outbound

This paper cites Egovqa-an egocentric video question answering benchmark dataset.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egovqa-an egocentric video question answering benchmark dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.366901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d09369-925b-4cb3-955f-c0ca4032c1ef · outbound

This paper cites Deep ordinal regression network for monocular depth estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Deep ordinal regression network for monocular depth estimation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.370801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a68823fd-3ddf-4389-a26b-3b300c8eedd2 · outbound

This paper cites Geowizard: Unleash- ing the diffusion priors for 3d geometry estimation from a single im- age.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Geowizard: Unleash- ing the diffusion priors for 3d geometry estimation from a single im- age

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.386825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f02a9a-0189-407b-8ee2-f0ac16bb1249 · outbound

This paper cites Unsu- pervised monocular depth estimation with left-right consistency.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Unsu- pervised monocular depth estimation with left-right consistency

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.496125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dfe3c77-c5b6-4d0e-9487-613d8a9f0a94 · outbound

This paper cites Digging into self-supervised monocular depth estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Digging into self-supervised monocular depth estimation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.635625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfd9642e-3138-4ad4-90fd-e6b1130a8b85 · outbound

This paper cites Depthfm: Fast generative monocular depth estimation with flow matching.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Depthfm: Fast generative monocular depth estimation with flow matching

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.715378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a72b5d-c784-499e-b672-ae41c181adca · outbound

This paper cites Towards zero-shot scale-aware monocular depth es- timation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Towards zero-shot scale-aware monocular depth es- timation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.800762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1043def6-f760-4ee6-a3ee-efca78ed658f · outbound

This paper cites an unresolved cited work.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.915084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d7ac6d-e563-47cd-95ef-b71a75f18254 · outbound

This paper cites Ego- taskqa: Understanding human tasks in egocentric videos.Advances in Neural Information Processing Systems, 35:3343–3360, 2022.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Ego- taskqa: Understanding human tasks in egocentric videos.Advances in Neural Information Processing Systems, 35:3343–3360, 2022

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:15.989903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bedfa933-1617-41d8-be95-6468ee25ca17 · outbound

This paper cites Repurposing diffusion- based image generators for monocular depth estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Repurposing diffusion- based image generators for monocular depth estimation

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.054865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aac8e7bc-8820-4dba-a97b-c697b76ec942 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.130687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2837398-d58e-4ca5-9547-b1366468f428 · outbound

This paper cites Egocross: Benchmarking multimodal large language models for cross- domain egocentric video question answering.arXiv preprint arXiv:2508.10729, 2025.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egocross: Benchmarking multimodal large language models for cross- domain egocentric video question answering.arXiv preprint arXiv:2508.10729, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.237961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee1175e-1636-415f-a0b1-67519baae3d8 · outbound

This paper cites BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.314451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b4ab995-c0aa-4481-b14c-79666e8cd61d · outbound

This paper cites Patchfusion: An end-to-end tile-based framework for high-resolution monocular met- ric depth estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Patchfusion: An end-to-end tile-based framework for high-resolution monocular met- ric depth estimation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.396078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e457fda-1d07-4c99-af11-3dc7964ebf5b · outbound

This paper cites Unibind: Llm-augmented unified and balanced representation space to bind them all.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Unibind: Llm-augmented unified and balanced representation space to bind them all

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.465821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63523dd7-515a-4f88-a91d-3a270c51eab6 · outbound

This paper cites Realrag: Retrieval- augmented realistic image generation via self-reflective contrastive learning.arXiv preprint arXiv:2502.00848, 2025.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Realrag: Retrieval- augmented realistic image generation via self-reflective contrastive learning.arXiv preprint arXiv:2502.00848, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.610317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a25bdb-33de-4010-8f4d-d7ec315278b4 · outbound

This paper cites Single image depth estimation: An overview.Digital Signal Processing, 123: 103441, 2022.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Single image depth estimation: An overview.Digital Signal Processing, 123: 103441, 2022

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.686243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75867d58-7767-4496-b5a4-60dd58376bac · outbound

This paper cites UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.809240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19aa8d47-db44-4ab3-8735-4d50f542d48e · outbound

This paper cites Towards robust monocular depth estimation: Mix- ing datasets for zero-shot cross-dataset transfer.IEEE transactions on pattern analysis and machine intelligence, 44(3):1623–1637,.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Towards robust monocular depth estimation: Mix- ing datasets for zero-shot cross-dataset transfer.IEEE transactions on pattern analysis and machine intelligence, 44(3):1623–1637,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.895759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa72a3f3-6776-49ce-a8db-4fe5854726ee · outbound

This paper cites Monocular depth estimation us- ing neural regression forest.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Monocular depth estimation us- ing neural regression forest

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:16.960864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e09c48aa-acf9-4216-90f2-c1c3b39690db · outbound

This paper cites Towards vqa models that can read.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Towards vqa models that can read

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.077636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f5c2a54-2c1c-46d1-a50e-8ff3b43a3dcf · outbound

This paper cites AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.186399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58287337-48c1-4af8-bd02-c2ce6333dd5b · outbound

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

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.304733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be175290-bc13-4f19-a30c-748ab95edd3e · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Emu3: Next-Token Prediction is All You Need

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.406676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f015b3-0808-4241-8a97-b5a6fd790104 · outbound

This paper cites Fastdepth: Fast monocular depth estimation on em- bedded systems.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Fastdepth: Fast monocular depth estimation on em- bedded systems

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.515648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 029520bc-4b9d-41fb-a7a1-c1ca069ee1b2 · outbound

This paper cites Visual question answering: A survey of methods and datasets.Computer Vision and Image Understanding, 163:21–40, 2017.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Visual question answering: A survey of methods and datasets.Computer Vision and Image Understanding, 163:21–40, 2017

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.647380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3001eee-3042-4fda-be0e-89e8fe23942b · outbound

This paper cites Egolife: Towards egocentric life assistant.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egolife: Towards egocentric life assistant

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.731562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0246b27-dfdb-4ffc-9442-702193a6e75b · outbound

This paper cites Depth anything v2.Advances in Neural Information Processing Systems, 37:21875–21911, 2024.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Depth anything v2.Advances in Neural Information Processing Systems, 37:21875–21911, 2024

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.802293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a8cce54-98b9-488c-ad2a-3b209436c2fe · outbound

This paper cites MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:17.934979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 967597eb-dbee-467e-b868-02cb603a993a · outbound

This paper cites Metric3d: Towards zero- shot metric 3d prediction from a single image.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Metric3d: Towards zero- shot metric 3d prediction from a single image

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:18.058550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 857d1fd3-24c7-4d7b-ad72-d2e06c774bbf · outbound

This paper cites NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:18.177460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ace98f0a-0237-417a-a0ad-8f059242d5c8 · outbound

This paper cites Egonight: Towards egocentric vision under- standing at night with a challenging benchmark.arXiv preprint arXiv:2510.06218, 2025.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egonight: Towards egocentric vision under- standing at night with a challenging benchmark.arXiv preprint arXiv:2510.06218, 2025

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:18.266673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9400028d-e145-47f0-830b-fc6eae73cfb5 · outbound

This paper cites Egotextvqa: Towards egocentric scene-text aware video question answering.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation Egotextvqa: Towards egocentric scene-text aware video question answering

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:18.334406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5169957-d4f4-42c6-8280-353bf109e023 · outbound

This paper cites ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos.

Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T01:59:18.438342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers