Synthetic Visual Genome | Paper Citation Record

Observation c9ca91f4-db87-41f0-9308-5317b565070e · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Synthetic Visual Genome Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.127801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73fd8e3d-13fd-4bc5-91dd-16ced5c8517d · outbound

This paper cites Tallyqa: Answering complex counting ques- tions.

Synthetic Visual Genome Tallyqa: Answering complex counting ques- tions

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.132663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843123ab-78cf-4147-84f2-f2d8413c7631 · outbound

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

Synthetic Visual Genome Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.136278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9a5cfc-9c79-4443-80c9-74e5fe85537e · outbound

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

Synthetic Visual Genome Qwen2.5- vl technical report, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.140227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66014a5f-486a-4ef1-92e2-077b1527a6a1 · outbound

This paper cites Recognition-by-components: a theory of human image understanding.

Synthetic Visual Genome Recognition-by-components: a theory of human image understanding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.144144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f78d3f8-944f-4c9a-9ef2-f66756f1db8b · outbound

This paper cites Scene perception: Detecting and judging objects undergoing relational violations.

Synthetic Visual Genome Scene perception: Detecting and judging objects undergoing relational violations

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.148080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621a401c-846a-4fd6-afa5-c5a7bb983f12 · outbound

This paper cites From machine learning to machine reasoning.

Synthetic Visual Genome From machine learning to machine reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.151726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd08e4b6-ef5d-4ff9-8482-d8609d25b6ac · outbound

This paper cites InternLM2 Technical Report.

Synthetic Visual Genome InternLM2 Technical Report

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.155396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35021869-bf88-43f1-9460-cb3d2a0777e9 · outbound

This paper cites Spa- tialvlm: Endowing vision-language models with spatial reasoning capabilities.

Synthetic Visual Genome Spa- tialvlm: Endowing vision-language models with spatial reasoning capabilities

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.159529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f834ca1-588e-46b7-89c7-957a58a15f21 · outbound

This paper cites Scene graph generation with role-playing large language models.

Synthetic Visual Genome Scene graph generation with role-playing large language models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.163039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8358cc76-c7f8-4885-b7fb-332f9af45017 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Synthetic Visual Genome MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.166607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fa95942-7b78-406d-8936-b133ca531c27 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

Synthetic Visual Genome Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.170431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d244ef11-44d7-4702-b2a3-f7b510f15722 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

Synthetic Visual Genome ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.174628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c5458fc-0d9c-488d-89e8-0b4b86bb8343 · outbound

This paper cites De- tect what you can: Detecting and representing ob- jects using holistic models and body parts.

Synthetic Visual Genome De- tect what you can: Detecting and representing ob- jects using holistic models and body parts

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.178591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f691a715-d436-4257-8bcd-78060c30bf35 · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

Synthetic Visual Genome How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.182129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef70ba1-f99b-4921-844d-63719bb87971 · outbound

This paper cites Some contro- versial questions in phonological theory.

Synthetic Visual Genome Some contro- versial questions in phonological theory

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.185764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81756ea0-0dde-4d05-999f-575bd59ad68b · outbound

This paper cites In- structblip: Towards general-purpose vision-language models with instruction tuning.

Synthetic Visual Genome In- structblip: Towards general-purpose vision-language models with instruction tuning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.189572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f543eb-c494-422b-adc3-d91eb5814d1d · outbound

This paper cites Data Filtering Networks.

Synthetic Visual Genome Data Filtering Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.193696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395a5a37-0c82-48f3-a1a5-3d79e44675ee · outbound

This paper cites BLINK: Multimodal Large Language Models Can See but Not Perceive.

Synthetic Visual Genome BLINK: Multimodal Large Language Models Can See but Not Perceive

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.197159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b73cc2f4-d977-494e-aa5a-28d386d440b8 · outbound

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

Synthetic Visual Genome Datacomp: In search of the next generation of multimodal datasets

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.200921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2d29edd-9cbb-4257-b5d7-93b45b8f30df · outbound

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

Synthetic Visual Genome Making the v in vqa matter: Elevating the role of image understand- ing in visual question answering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.204191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fd1fe8b-843f-4466-af2e-9ff1de480b38 · outbound

This paper cites Agqa: A benchmark for compo- sitional spatio-temporal reasoning.

Synthetic Visual Genome Agqa: A benchmark for compo- sitional spatio-temporal reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.207859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a66fd0b3-7f33-4b05-9ecc-14e3e9fb574f · outbound

This paper cites Lvis: A dataset for large vocabulary instance segmenta- tion.

Synthetic Visual Genome Lvis: A dataset for large vocabulary instance segmenta- tion

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.211197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 154f2970-d1c7-477c-93c8-ddc2a9d89bf3 · outbound

This paper cites Dsgg: Dense rela- tion transformer for an end-to-end scene graph gener- 10 ation.

Synthetic Visual Genome Dsgg: Dense rela- tion transformer for an end-to-end scene graph gener- 10 ation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.214266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 190fa380-8023-4ef3-bfb2-d265879ed3ef · outbound

This paper cites Partim- agenet: A large, high-quality dataset of parts, 2022.

Synthetic Visual Genome Partim- agenet: A large, high-quality dataset of parts, 2022

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.217733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d507d362-1e83-4122-8850-e25e00a3b9dc · outbound

This paper cites The curious case of neural text degenera- tion, 2020.

Synthetic Visual Genome The curious case of neural text degenera- tion, 2020

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.221442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6b91b7f-3fb6-4f52-a138-ac68540b9a43 · outbound

This paper cites Sugarcrepe: Fixing hackable benchmarks for vision-language composi- tionality.

Synthetic Visual Genome Sugarcrepe: Fixing hackable benchmarks for vision-language composi- tionality

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.224704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8653c0d0-3872-4fc3-b731-81a48967ace8 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

Synthetic Visual Genome Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.228027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55462a7-4705-4134-b514-5ab167e9c7af · outbound

This paper cites Compositionality decomposed: How do neural networks generalise? Journal of Artificial Intelligence Research, 67:757–795, 2020.

Synthetic Visual Genome Compositionality decomposed: How do neural networks generalise? Journal of Artificial Intelligence Research, 67:757–795, 2020

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.231437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38c3e5d5-f37f-422b-ab2c-fa3c6f24cdf9 · outbound

This paper cites Openclip, 2021.

Synthetic Visual Genome Openclip, 2021

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.234735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb09afa-beb7-4308-8720-fc42fe779bdf · outbound

This paper cites Composi- tionality.

Synthetic Visual Genome Composi- tionality

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.239075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e390da5c-37bf-4155-a1ff-cf3b648340c5 · outbound

This paper cites Action genome: Actions as compositions of spatio-temporal scene graphs.

Synthetic Visual Genome Action genome: Actions as compositions of spatio-temporal scene graphs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.242711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e680ed8a-74b7-43bb-a857-0c7330884c8f · outbound

This paper cites Dvqa: Understanding data visualiza- tions via question answering.

Synthetic Visual Genome Dvqa: Understanding data visualiza- tions via question answering

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.246134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3637a4dc-3f5b-473d-ba09-dd7a31d99e13 · outbound

This paper cites What’s “up” with vision-language models? inves- tigating their struggle with spatial reasoning.

Synthetic Visual Genome What’s “up” with vision-language models? inves- tigating their struggle with spatial reasoning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.249666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95fe4f56-daef-4ca4-a7de-5b3962301881 · outbound

This paper cites What's "up" with vision-language models? Investigating their struggle with spatial reasoning.

Synthetic Visual Genome What's "up" with vision-language models? Investigating their struggle with spatial reasoning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.253961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 759036f5-8542-4cb1-bcc5-5065eaf3e1a7 · outbound

This paper cites A diagram is worth a dozen images.

Synthetic Visual Genome A diagram is worth a dozen images

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.258047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a2d4fb-fef0-4c76-9bfc-27edab966a79 · outbound

This paper cites Are you smarter than a sixth grader? textbook ques- tion answering for multimodal machine comprehen- sion.

Synthetic Visual Genome Are you smarter than a sixth grader? textbook ques- tion answering for multimodal machine comprehen- sion

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.261392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c30a0e-ed8d-4f06-b883-65e6aa4ccace · outbound

This paper cites Llm4sgg: Large language models for weakly supervised scene graph generation.

Synthetic Visual Genome Llm4sgg: Large language models for weakly supervised scene graph generation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.264742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb438b5b-3fed-4aa8-b934-e8b48cb7dc27 · outbound

This paper cites Segment anything.

Synthetic Visual Genome Segment anything

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.268064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a750bf21-1158-4bf8-a17b-7c2422b5bf1c · outbound

This paper cites Vi- sual genome: Connecting language and vision using crowdsourced dense image annotations.

Synthetic Visual Genome Vi- sual genome: Connecting language and vision using crowdsourced dense image annotations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.271522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be22b953-e045-4b7e-bea5-142f24c67f0e · outbound

This paper cites The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale.

Synthetic Visual Genome The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.275008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dcedcd2-9f0c-4a1e-8edc-af5cc08444e2 · outbound

This paper cites Seed-bench: Benchmark- ing multimodal llms with generative comprehension,.

Synthetic Visual Genome Seed-bench: Benchmark- ing multimodal llms with generative comprehension,

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.278599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a0653aa-0fc1-4e56-941e-561e8d0613b9 · outbound

This paper cites MIMIC-IT: Multi-Modal In-Context Instruction Tuning.

Synthetic Visual Genome MIMIC-IT: Multi-Modal In-Context Instruction Tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.282191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c563c1f1-84d0-439a-8963-fdd760c74134 · outbound

This paper cites Semantic-SAM: Segment and Recognize Anything at Any Granularity.

Synthetic Visual Genome Semantic-SAM: Segment and Recognize Anything at Any Granularity

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.285746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 766c363b-2435-485a-9584-d459cccf1692 · outbound

This paper cites Sgtr: End-to-end scene graph generation with transformer,.

Synthetic Visual Genome Sgtr: End-to-end scene graph generation with transformer,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.289546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a265df5-0964-4b0b-b059-1afef75098d4 · outbound

This paper cites From pixels to graphs: Open-vocabulary scene graph generation with vision- language models.

Synthetic Visual Genome From pixels to graphs: Open-vocabulary scene graph generation with vision- language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.293393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 635def2f-8e23-415f-9fc8-08656c6d96d6 · outbound

This paper cites Vila: On pre- training for visual language models.

Synthetic Visual Genome Vila: On pre- training for visual language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.296832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c89f1ff3-2383-41d9-a704-350217b7092b · outbound

This paper cites Microsoft coco: Common ob- jects in context.

Synthetic Visual Genome Microsoft coco: Common ob- jects in context

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.300186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bbfaad7-dd63-4ff1-bb67-0ea68d42726e · outbound

This paper cites Gps-net: Graph property sensing net- work for scene graph generation.

Synthetic Visual Genome Gps-net: Graph property sensing net- work for scene graph generation

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.303622Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65d36ee-664b-42cb-9df9-cc0cc0047354 · outbound

This paper cites Visual spatial reasoning.

Synthetic Visual Genome Visual spatial reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.307221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e7f6793-a6dc-4679-aff5-253e0caae909 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Synthetic Visual Genome Improved Baselines with Visual Instruction Tuning

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.311317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15a46ba1-9ef2-446b-9248-f2b7ee21e784 · outbound

This paper cites Visual instruction tuning.

Synthetic Visual Genome Visual instruction tuning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.314772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70118e8b-c904-40d3-9813-714408d96a84 · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

Synthetic Visual Genome MMBench: Is Your Multi-modal Model an All-around Player?

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.318290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1869da5b-7dd9-49ec-a545-6c6675d21df2 · outbound

This paper cites Visual relationship detection with lan- guage priors.

Synthetic Visual Genome Visual relationship detection with lan- guage priors

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.322396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26960e45-f922-484b-b6c3-8607b1f17359 · outbound

This paper cites Groma: Localized visual tokeniza- tion for grounding multimodal large language models.

Synthetic Visual Genome Groma: Localized visual tokeniza- tion for grounding multimodal large language models

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.326676Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e733bdb7-1ab0-4e90-8320-9be7a0267600 · outbound

This paper cites Crepe: Can vision-language foundation models reason compositionally? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10910–10921, 2023.

Synthetic Visual Genome Crepe: Can vision-language foundation models reason compositionally? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10910–10921, 2023

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.330051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31eff2e7-03e2-44ae-b24d-53656fde7692 · outbound

This paper cites Generation and comprehension of unambigu- ous object descriptions.

Synthetic Visual Genome Generation and comprehension of unambigu- ous object descriptions

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.333507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d3683ad-d4d0-4391-aef0-f33890610358 · outbound

This paper cites Ok-vqa: A visual ques- tion answering benchmark requiring external knowl- edge.

Synthetic Visual Genome Ok-vqa: A visual ques- tion answering benchmark requiring external knowl- edge

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.337199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ce88af0-17bb-4942-a2a3-475cb895b420 · outbound

This paper cites ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning.

Synthetic Visual Genome ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.340682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb224d5c-7609-41b4-aaa3-bcfa16c183f5 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

Synthetic Visual Genome Docvqa: A dataset for vqa on document images

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.344278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b38f56ce-fee3-45bf-a545-1ee82014b56b · outbound

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

Synthetic Visual Genome MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.348041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6949f4a-3c2e-4c82-a8a2-dcd9a9d65efd · outbound

This paper cites an unresolved cited work.

Synthetic Visual Genome Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.351500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97576187-3383-4a1d-926a-33255125e53c · outbound

This paper cites Localized Symbolic Knowledge Distillation for Visual Commonsense Models.

Synthetic Visual Genome Localized Symbolic Knowledge Distillation for Visual Commonsense Models

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-08-07T05:34:56.947759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fb21d42a-4bde-4359-b3ee-1eeef744921a · outbound

This paper cites Kosmos-2: Grounding Multimodal Large Language Models to the World.

Synthetic Visual Genome Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.359405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ba8dee-bad6-40fe-9d86-df044fb927b7 · outbound

This paper cites Plummer, Liwei Wang, Chris M.

Synthetic Visual Genome Plummer, Liwei Wang, Chris M

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.362597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6f9ad47-2c09-4d16-af02-02e7b913a977 · outbound

This paper cites Filtering, distillation, and hard negatives for vision-language pre-training.

Synthetic Visual Genome Filtering, distillation, and hard negatives for vision-language pre-training

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.366288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bdbdeca-8d3e-48e5-9c34-bf342391da66 · outbound

This paper cites Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sas- try, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.

Synthetic Visual Genome Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sas- try, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.369936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5049823-3312-44d8-b173-26fb24d6fac1 · outbound

This paper cites Paco: Parts and attributes of common ob- jects.

Synthetic Visual Genome Paco: Parts and attributes of common ob- jects

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.373066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22d2aca9-be99-406e-815d-a7e7aa6b1e77 · outbound

This paper cites GLaMM: Pixel Grounding Large Multimodal Model.

Synthetic Visual Genome GLaMM: Pixel Grounding Large Multimodal Model

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.376390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c95e9ec-8b78-4775-bd19-2cbad3b59826 · outbound

This paper cites Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters.

Synthetic Visual Genome Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.381288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60fd5677-cd24-47eb-ae44-fc60fea3642e · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

Synthetic Visual Genome Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.384658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99543457-7f41-4236-9855-6ac962b887b3 · outbound

This paper cites Scienceqa: A novel resource for question answering on scholarly articles.

Synthetic Visual Genome Scienceqa: A novel resource for question answering on scholarly articles

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.388383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2057fdbb-aa2b-4505-b9f1-b5910432c66d · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

Synthetic Visual Genome LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.391967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1431c41e-45dc-44f0-b397-12802c2e6d23 · outbound

This paper cites A- okvqa: A benchmark for visual question answering using world knowledge.

Synthetic Visual Genome A- okvqa: A benchmark for visual question answering using world knowledge

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.395633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62c8d675-5ca3-418f-9b30-17d5781275cc · outbound

This paper cites Textcaps: a dataset for image captioning with reading comprehension.

Synthetic Visual Genome Textcaps: a dataset for image captioning with reading comprehension

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.398911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 932b6292-a847-48c3-bbbd-467b58400c35 · outbound

This paper cites Learning to compose dynamic tree structures for visual contexts.

Synthetic Visual Genome Learning to compose dynamic tree structures for visual contexts

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.402470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0fea6cf-5322-4cb4-9a35-899011ecac55 · outbound

This paper cites Unbiased scene graph generation from biased training.

Synthetic Visual Genome Unbiased scene graph generation from biased training

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.405973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36dcad90-d463-478d-9e41-baf1443bfe0c · outbound

This paper cites Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models.

Synthetic Visual Genome Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.409537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b104c79-3288-4e23-94d8-f6495d894c86 · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

Synthetic Visual Genome CogVLM: Visual Expert for Pretrained Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.413258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c70c81f-6cc8-4285-b0ae-3ba391976aeb · outbound

This paper cites Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters.

Synthetic Visual Genome Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.416946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7760941-faf7-4006-b315-c3ce95d6a50b · outbound

This paper cites The all-seeing project v2: Towards gen- eral relation comprehension of the open world, 2024.

Synthetic Visual Genome The all-seeing project v2: Towards gen- eral relation comprehension of the open world, 2024

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.563117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb482150-f3de-4131-8e6a-9f0a12eecc9b · outbound

This paper cites Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks.

Synthetic Visual Genome Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.424085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff2ee90-61f0-4ad2-88af-dc5d121c97ec · outbound

This paper cites VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks.

Synthetic Visual Genome VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.427639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b5ebf0-12e0-4221-84d3-d315d3dda227 · outbound

This paper cites Scene graph generation by iterative message passing.

Synthetic Visual Genome Scene graph generation by iterative message passing

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.551650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e17624a3-2449-4eed-9fcd-06ae8670e146 · outbound

This paper cites xgen-mm (blip-3): A family of open large multimodal models.

Synthetic Visual Genome xgen-mm (blip-3): A family of open large multimodal models

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.434261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb319264-96bb-4058-8a55-93a1f50e3353 · outbound

This paper cites Qwen2 Technical Report.

Synthetic Visual Genome Qwen2 Technical Report

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.437648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a79a29-10c2-4eae-b2cc-344f781e72f3 · outbound

This paper cites Panoptic scene graph generation.

Synthetic Visual Genome Panoptic scene graph generation

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.541562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 490020ae-2146-45f2-9d49-c7f6978ec42a · outbound

This paper cites Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V.

Synthetic Visual Genome Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.444424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e564cc03-3c19-4c0a-bca7-aed2b9d4722e · outbound

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

Synthetic Visual Genome Depth any- thing: Unleashing the power of large-scale unlabeled data

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.531233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0b651cdb-e637-436e-93fe-b8a1eb327107 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

Synthetic Visual Genome MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.450803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ea739e7-06be-4d83-b0a8-81b1af7d4232 · outbound

This paper cites mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration.

Synthetic Visual Genome mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.454152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f06bb5-545d-471d-9d18-ede5f479399b · outbound

This paper cites Ferret: Refer and Ground Anything Anywhere at Any Granularity.

Synthetic Visual Genome Ferret: Refer and Ground Anything Anywhere at Any Granularity

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.457915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe124c37-9cd8-4e7d-93a7-4452f29765aa · outbound

This paper cites Modeling context in referring expressions.

Synthetic Visual Genome Modeling context in referring expressions

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.521049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c17ffcaa-4999-47a3-b668-0dc29a7a7116 · outbound

This paper cites Modeling context in re- ferring expressions.

Synthetic Visual Genome Modeling context in re- ferring expressions

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.511279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4f8809ee-4581-45f2-810f-dae7712da24b · outbound

This paper cites Rlip: Relational language-image pre-training for human-object interaction detection, 2022.

Synthetic Visual Genome Rlip: Relational language-image pre-training for human-object interaction detection, 2022

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.501079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3af32829-0125-4437-b825-8da297d5b11f · outbound

This paper cites Os- prey: Pixel understanding with visual instruction tun- ing, 2024.

Synthetic Visual Genome Os- prey: Pixel understanding with visual instruction tun- ing, 2024

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.490871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ad533fb-5a44-41fa-90ef-c9d01c30bbff · outbound

This paper cites Neural motifs: Scene graph pars- ing with global context.

Synthetic Visual Genome Neural motifs: Scene graph pars- ing with global context

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.480480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 20a541f8-b032-4737-8af2-a408fd3198b7 · outbound

This paper cites From recognition to cognition: Vi- sual commonsense reasoning.

Synthetic Visual Genome From recognition to cognition: Vi- sual commonsense reasoning

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T05:34:57.470192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c210b42b-8c9b-405b-81ac-53a1ea037dab · outbound

This paper cites LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models.

Synthetic Visual Genome LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.481852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b467c74-ff80-4c1a-951d-140c60b59b96 · outbound

This paper cites MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning.

Synthetic Visual Genome MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T05:34:56.485538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers