VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization | Paper Citation Record

Observation 29dfd4c0-64c6-4a2c-acdd-19fef097dacb · outbound

This paper cites Docformer: End-to-end transformer for document understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Docformer: End-to-end transformer for document understanding

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.872435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5508c845-f007-4386-b509-bdb252ee4268 · outbound

This paper cites Qwen-vl: A versatile vision-language model for un- derstanding, localization.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Qwen-vl: A versatile vision-language model for un- derstanding, localization

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.717043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 39ece4dc-3400-49d9-a18a-1fba010b1dc6 · outbound

This paper cites Due: End-to-end document understand- ing benchmark.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Due: End-to-end document understand- ing benchmark

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.610275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e0ffee70-b30d-4c9a-a799-f5fae76f8f5d · outbound

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

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:02.588039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be0e5316-1b31-4aa0-94eb-a6704667ce56 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Gonzalez, Ion Stoica, and Eric P

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.523868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad2367e2-b82d-45f9-8574-151d13ee6d98 · outbound

This paper cites Instructblip: towards general- purpose vision-language models with instruction tuning.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Instructblip: towards general- purpose vision-language models with instruction tuning

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.377660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2562b1e0-86bb-4dd2-b276-104e062ac7ab · outbound

This paper cites Docpedia: Unleashing the power of large multimodal model in the frequency domain for versatile document understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Docpedia: Unleashing the power of large multimodal model in the frequency domain for versatile document understanding

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.224822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 72ea372f-a773-49ab-b868-f35ea1b0ddd1 · outbound

This paper cites Unidoc: Unified pretraining framework for document understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Unidoc: Unified pretraining framework for document understanding

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:15.072082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e1a838da-28c7-4965-8f29-5a4561e6547e · outbound

This paper cites Deep residual learning for image recognition.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Deep residual learning for image recognition

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:14.952677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b584473d-7079-4be1-ace2-70cadbd24256 · outbound

This paper cites Gaussian Error Linear Units (GELUs).

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Gaussian Error Linear Units (GELUs)

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:03.420452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fec0b0f-ce6d-4e54-ad0f-301f5e9fcad5 · outbound

This paper cites Cogagent: A visual language model for gui agents.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Cogagent: A visual language model for gui agents

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:14.780291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 33ee729d-cb83-4a84-8245-2eb18fe80198 · outbound

This paper cites SciCap: Generating captions for scientific figures.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization SciCap: Generating captions for scientific figures

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:14.636710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d7737523-5de0-43c3-a758-44fe24b45c1a · outbound

This paper cites mPLUG-DocOwl 1.5: Unified structure learning for OCR- free document understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization mPLUG-DocOwl 1.5: Unified structure learning for OCR- free document understanding

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:14.349022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9bff7f50-ba8c-4efd-80dd-554c471ec62a · outbound

This paper cites Lora: Low-rank adaptation of large language models.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Lora: Low-rank adaptation of large language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:03.901686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6606b3e1-991a-42ff-b0e2-62480fe7f54c · outbound

This paper cites Layoutlmv3: Pre-training for document ai with unified text and image masking.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Layoutlmv3: Pre-training for document ai with unified text and image masking

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:14.125109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 85147d98-064b-4328-8385-1b3d0f26df68 · outbound

This paper cites Icdar2019 compe- tition on scanned receipt ocr and information extraction.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Icdar2019 compe- tition on scanned receipt ocr and information extraction

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.931638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bc7d70da-177f-46f5-99f3-9c8024905df1 · outbound

This paper cites Funsd: A dataset for form understanding in noisy scanned documents.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Funsd: A dataset for form understanding in noisy scanned documents

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.748786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 320e75f1-9534-4125-b13f-1c8c709c3879 · outbound

This paper cites A diagram is worth a dozen images.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization A diagram is worth a dozen images

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:04.251928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc00b05-2fac-41d0-b892-0692a689a5ee · outbound

This paper cites OCR-free Document Understanding Transformer.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization OCR-free Document Understanding Transformer

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:04.304286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6689e449-4978-47f0-ae20-f53b79396df4 · outbound

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

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.530535Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7f6cae0-596e-4cba-adb2-cdd848a8e768 · outbound

This paper cites DocBank: A bench- mark dataset for document layout analysis.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization DocBank: A bench- mark dataset for document layout analysis

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.380065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9729aeed-e6c8-4829-95ab-5a0d911f373b · outbound

This paper cites Selfdoc: Self-supervised document representation learning.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Selfdoc: Self-supervised document representation learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.238668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c7a26764-3cc7-479d-8571-a0fc72c79c92 · outbound

This paper cites Mon- key: Image resolution and text label are important things for large multi-modal models.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Mon- key: Image resolution and text label are important things for large multi-modal models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:13.072147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e2683014-4149-4068-9dce-8ebb7e5ef479 · outbound

This paper cites DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:04.645195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ad7ffd0-f94a-426d-80db-5125b053fac6 · outbound

This paper cites Microsoft coco: Common objects in context.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Microsoft coco: Common objects in context

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:04.806022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d80c291-eed3-44fe-9945-e8fa849f5100 · outbound

This paper cites Feature pyra- mid networks for object detection.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Feature pyra- mid networks for object detection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:04.947845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7fb894e-2d7d-48e7-8cc2-7cd6a526d8ac · outbound

This paper cites Visual instruction tuning.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Visual instruction tuning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.026870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02842439-b046-4944-b9c5-5a46b0a4d168 · outbound

This paper cites Improved baselines with visual instruction tuning.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Improved baselines with visual instruction tuning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:12.802843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cc6f6b2f-255c-40f5-b1df-25125e92583b · outbound

This paper cites TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.251861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691dc397-de21-4031-8702-cf906a213fb4 · outbound

This paper cites Swin transformer v2: Scaling up capacity and resolution.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Swin transformer v2: Scaling up capacity and resolution

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:12.531717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f052739d-9cc9-4a47-94f9-cabd4510cc10 · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.416342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7544abc3-553f-4d8b-90f1-89d96377dff3 · outbound

This paper cites Decoupled Weight Decay Regularization.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Decoupled Weight Decay Regularization

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.480905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90a8901b-f628-45d3-a1e1-3cf2a4e7b441 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.531100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e38e9f-cae0-47d4-9c06-2aae302fb3f7 · outbound

This paper cites DocVQA: A Dataset for VQA on Document Images.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization DocVQA: A Dataset for VQA on Document Images

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:05.622333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e1d906-ab40-46a0-bc34-7c2a5cd57de4 · outbound

This paper cites Azure Cognitive Services: Optical Char- acter Recognition (OCR).

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Azure Cognitive Services: Optical Char- acter Recognition (OCR)

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:12.216896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bc0fdc9f-f52d-4fb0-a1f5-a8e1a0ee34e9 · outbound

This paper cites Rectified linear units im- prove restricted boltzmann machines.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Rectified linear units im- prove restricted boltzmann machines

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:11.930770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc51e973-6da0-455a-a2b2-dc51d816a9c2 · outbound

This paper cites Cord: a con- solidated receipt dataset for post-ocr parsing.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Cord: a con- solidated receipt dataset for post-ocr parsing

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:11.644166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0534d87b-bb01-452c-bb25-29b97a652f07 · outbound

This paper cites Automatic differentiation in pytorch.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Automatic differentiation in pytorch

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:11.417501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 400d844d-0b27-4646-8b4a-c68848708a74 · outbound

This paper cites Doclaynet: A large human- annotated dataset for document-layout segmentation.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Doclaynet: A large human- annotated dataset for document-layout segmentation

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:11.171317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 519d9a20-7fff-4027-8483-af81641f1a3a · outbound

This paper cites Going full-tilt boogie on document understanding with text-image-layout transformer.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Going full-tilt boogie on document understanding with text-image-layout transformer

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:06.153026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5761f58d-16d5-448b-9b94-5b221ebb6dd6 · outbound

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

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Deepspeed: System optimizations enable train- ing deep learning models with over 100 billion parameters

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:09.968066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5ef67d07-a8dc-41dc-9d26-cb56b53ddcc9 · outbound

This paper cites Faster r-cnn: Towards real-time object detection with region proposal networks.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Faster r-cnn: Towards real-time object detection with region proposal networks

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:06.292975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9c86612-5a36-4025-a683-38c90fd824d6 · outbound

This paper cites Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:59:07.936194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0450fa45-eb9f-42af-997c-a167f0ea5ae5 · outbound

This paper cites Docile benchmark for document information localization and extraction.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Docile benchmark for document information localization and extraction

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:09.303856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4f4ff3ee-551a-480a-b2f8-3c623614cef3 · outbound

This paper cites Towards vqa models that can read.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Towards vqa models that can read

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:06.508889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7927cf82-2d59-4f37-a184-cef2e104c169 · outbound

This paper cites Spatial Dual-Modality Graph Reasoning for Key Information Extraction.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Spatial Dual-Modality Graph Reasoning for Key Information Extraction

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:06.590430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe05721-78e1-4dea-a77f-29a5e9be424e · outbound

This paper cites Instructdoc: A dataset for zero-shot general- ization of visual document understanding with instructions.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Instructdoc: A dataset for zero-shot general- ization of visual document understanding with instructions

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:09.108724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1fda786d-7401-4228-913d-144790c9ec8e · outbound

This paper cites Docllm: A layout-aware gener- ative language model for multimodal document understand- ing.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Docllm: A layout-aware gener- ative language model for multimodal document understand- ing

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.900312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 93db90e9-a191-4f32-86b2-5df0d338957e · outbound

This paper cites Vision-enhanced semantic entity recognition in document images via visually-asymmetric consistency learning.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Vision-enhanced semantic entity recognition in document images via visually-asymmetric consistency learning

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.765536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9212ef6d-d603-452e-9f5f-855e5e9601d3 · outbound

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

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:06.956279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6292d008-1c23-4547-8c70-31718d9802ac · outbound

This paper cites Layoutlm: Pre-training of text and layout for document image understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Layoutlm: Pre-training of text and layout for document image understanding

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.562604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 86758d95-0187-4e1b-bf58-47ca6d7d7f53 · outbound

This paper cites Layoutlmv2: Multi-modal pre-training for visually-rich document understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization Layoutlmv2: Multi-modal pre-training for visually-rich document understanding

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.414877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2454a794-357c-430c-9d0d-367ccdaf14d4 · outbound

This paper cites mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:07.342834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7ea86d-7888-4a3b-a0d7-2bf2eeb9d5ad · outbound

This paper cites UReader: Universal OCR-free visually-situated language understand- ing with multimodal large language model.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization UReader: Universal OCR-free visually-situated language understand- ing with multimodal large language model

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.280511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 249d394c-c77b-4bbf-8550-f94411c7e77b · outbound

This paper cites By my eyes: Grounding multimodal large language models with sensor data via vi- sual prompting.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization By my eyes: Grounding multimodal large language models with sensor data via vi- sual prompting

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T17:59:08.118046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cd4dc51e-b3e7-4372-80dd-ac741b1daf00 · outbound

This paper cites StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-08-06T17:59:07.773014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a888602-e291-42c8-9625-1461a92fcc8a · outbound

This paper cites LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding.

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T17:59:07.601054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers