Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-11T20:14:56.957808Z
Paper Citation Record · LEDGER
As of 15 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2412.05939.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-11T20:14:56.957808Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-07T04:08:49.205080Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-07T04:08:53.251034Z
62 of 62 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 86f25a70-1968-4825-9dae-671de663f430 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models For V3Det, we remove object labels with frequency less than 3
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a5cad1f9-2016-4227-a1f4-9f34a0e70bbc · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models For Open Images, we also remove the attribute and relationship annotations corresponding to these illegal objects
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation f9b63835-85f7-4e18-920c-2878327796c7 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e0b271e5-88d5-4254-9a0a-9dc682c5aaca · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0155ab72-192d-4ae9-bf5c-69e738d3b83b · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Kosmos-G: Generating Images in Context with Multimodal Large Language Models
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 45c5c501-d04e-4eed-9241-6db4752e7282 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a92aea54-cee4-49cf-a20e-bbf5f78850c7 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4221501a-1918-4bea-8614-57970eebe879 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Instance Location, Instance Interaction, Visual Reasoning
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ac2d4aa7-6bb6-479f-bea7-641b89a52f69 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models batter” → “batter (ballplayer)
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c0873608-b736-45ac-9afd-fb45da685f55 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c5a1cfe8-9b7e-4f10-a233-42a0a8ddadce · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models We also remove objects that have illegal coordinates or exceed the image range
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation c7945383-35f1-401b-b4da-ad271d5fc579 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models batter (baseball player)
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8d579735-5c71-4d73-84fc-8c55deca54ee · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Secondly, we count the frequency of each label and remove the relationship/attribute whose frequency is less than 5 or is empty
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation f226edde-00bf-43a5-aff0-97bc67061d68 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models For unreasonable labels, we remove them and the corresponding object, attribute, relationship annotations
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 721bb45c-afd5-4a19-aff7-7a214836a14a · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models For images in Visual Genome with a flickr id but no coco id, we match them with images from flickr30k and discard the matched images
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 7e644ff2-037f-45e2-aab5-90bd5ef6d20b · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b269db73-6e28-47a0-8c7f-f8e7e69c1a18 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 09ea4dcf-48be-4e8f-a650-148acc8c3fbc · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 8a654fef-8175-49e6-8b7a-aec90030e681 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models If no caption is selected, we select the caption with the highest similarity score
Reference 24
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 06726344-e681-4c39-93f0-09151dad2b41 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 25
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a0564405-1a01-46bb-853f-e2c80319cc88 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Then we remove the descriptions with a probability of 0.5 to prevent model overfitting which might be caused by description repetitions
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 43fd7009-d5be-4af5-97a4-1059c595e0fe · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Secondly, we replace the positions corresponding to [IMG] using the corresponding visual token sequence with [IMG] and [/IMG] inserted before and after it
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 3de25e1a-7e59-4147-9c2f-b1c700c67a68 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Detail caption instruction
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b691cb9d-7568-48f6-b98e-4aa16fd688c0 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models It resembles a large pig in shape, with a short, prehensile trunk, small eyes, and pointed ears
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0519d2f5-0252-4ab0-a65f-d3e0211374c9 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 2d961eb4-017f-44ab-a950-fcad9217b560 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a51a9a2f-4dcd-4008-8ed2-79b2804f6a91 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Invalid
Reference 55
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation affb92a0-1eff-4e38-8e0f-e2cc83875be5 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 56
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 75b02bc5-aa7e-47dc-b5d7-cad946c8eb48 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models bank" can be
Reference 57
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a0339240-6c81-40bc-87cd-de5c3b242f34 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 58
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 281220d6-3bd4-4e0d-a4bb-9feb09e8a820 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 59
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 68c69e42-74df-48b6-9991-fb999ac6bdfc · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 60
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation d650eeb7-eff4-49bc-a673-aa397f412c06 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 61
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ce8b98ca-f938-4d59-94da-9b3563f19a93 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 62
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation e3faae6e-4259-4b79-8b79-bd6341123dac · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 63
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 57503e9a-58a7-45fe-9b9d-1c111516f92e · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models It resembles a large pig in shape, with a short, prehensile trunk, small eyes, and pointed ears
Reference 64
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a50e25e3-dbd5-4daf-8b7b-7d60b8ac0865 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models You should disregard such noisy related object category labels
Reference 65
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4e59bed0-60a3-47be-8066-2563ae115bbe · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Invalid
Reference 66
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 1bcbf797-8b54-41ad-aa3c-f275ccc6c8c5 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 67
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 944e42b5-1637-4941-ad15-4f07377809b9 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models awake" is an adjective meaning
Reference 68
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 81bbfac1-3456-4fec-a690-53007260ab16 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 69
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5e620f1d-68cb-497d-8c49-8a682df32f14 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models This could include color, texture, size, sense, function, or any other aspect that is significant for the attribute
Reference 70
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 0e570504-a0c5-42d7-a12e-e03e1e8f00d4 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 72
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 655bf87d-0e9c-4998-b3ef-2405c4ffd2bf · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 73
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation ac8ec7ac-92ae-474e-a315-d06c74cd9b71 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 74
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 5d88c803-46d2-4798-a5d0-5573a947c182 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 75
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation a355aaf7-9168-4951-a55a-2eed8ba73a3d · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models You should disregard such noisy related subject-object pairs
Reference 76
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 81f6b493-0395-430a-ac4a-19a4eb9ab7bd · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Invalid
Reference 77
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation cd1b12ae-76e7-44cf-94d1-bac08b549f42 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 78
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation b05feb79-3c19-48c9-8e92-48675d611573 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models truck" is a verb meaning
Reference 79
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 92c49432-a71a-4b07-86f6-45f57dfa5bca · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 80
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 4e06afea-dec1-444e-968a-31315f7b6077 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 81
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 05b88217-8654-4797-8dac-4d9ecc3f690a · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 82
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 787e0036-dc03-4bd0-a464-17a8b200dc51 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 83
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 65c93dfd-705a-4ada-8311-0dd09b613d2c · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 84
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 581a4a09-43f8-4b62-be63-e3023a6cdd1f · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 85
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 46f9acb5-0418-4f93-b16d-991c0803011f · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Unresolved cited work
Reference 86
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation 2f2a07b9-944d-48f7-a44b-67673b7d04d3 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models batter” → “batter (ballplayer)
Reference 2020
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.
Observation bfcab0fe-e17e-4378-bde6-f566bc15f339 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
Reference 2021
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0818035c-79c4-4ac0-9e41-2f9af1ac53ef · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Reference 2023
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f3705c9-8c74-4031-8864-94d81dbc2805 · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models Microsoft COCO Captions: Data Collection and Evaluation Server
Reference 2024
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c98f3d26-ca9a-4f3d-bff0-47e10caeb27a · outbound
Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models doi: 10.1109/CVPR.2019.00686
Reference 6709
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a2673b7b-bbbd-415f-820a-73268831873c · inbound
Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models
Reference 110
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.