Thinking with Anchors: Grounded and Efficient Document Reasoning | Paper Citation Record

Observation 079bbeaa-c242-4e64-a758-45ab268f868c · outbound

This paper cites Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models.

Thinking with Anchors: Grounded and Efficient Document Reasoning Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.228681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b87716f9-dcfd-40a0-af94-57f6162a546d · outbound

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

Thinking with Anchors: Grounded and Efficient Document Reasoning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.289120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 939ed157-f89f-4cd0-a570-61b9b2513a3d · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Thinking with Anchors: Grounded and Efficient Document Reasoning Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.396919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79d40e6c-d860-48e4-b6e4-e7da9681bfde · outbound

This paper cites End-to-end object detection with transformers.

Thinking with Anchors: Grounded and Efficient Document Reasoning End-to-end object detection with transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.482296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6930afa3-d89e-458e-9e14-2c151e7cf105 · outbound

This paper cites SAM 3: Segment Anything with Concepts.

Thinking with Anchors: Grounded and Efficient Document Reasoning SAM 3: Segment Anything with Concepts

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.560859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89998913-626c-4f99-961b-318e76ce9386 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.668507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0320ae71-272c-496b-a799-9bf9b37f32e5 · outbound

This paper cites Chaudhuri (ed.).Digital Document Processing: Major Directions and Recent Advances.

Thinking with Anchors: Grounded and Efficient Document Reasoning Chaudhuri (ed.).Digital Document Processing: Major Directions and Recent Advances

Reference 7

Resolution: verified exact; doi, observed 2026-08-07T00:24:55.084014Z

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 e98c58e3-c3ae-46d7-a90a-f9730d9cc96c · outbound

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

Thinking with Anchors: Grounded and Efficient Document Reasoning Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.866113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c6f4780-02ba-4b86-a7b7-c98724fa0f1b · outbound

This paper cites Fleet, and Geoffrey Hinton.

Thinking with Anchors: Grounded and Efficient Document Reasoning Fleet, and Geoffrey Hinton

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:48.955959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 551169d8-3bc3-46a9-a6e6-38a9398158c3 · outbound

This paper cites Graph-based document structure analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning Graph-based document structure analysis

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.064174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fae058d-1240-417b-8472-f9b57fc96786 · outbound

This paper cites M6doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning M6doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.180375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 533c0f0d-e1e9-40c4-a446-fb04145dc1f4 · outbound

This paper cites M 6Doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning M 6Doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.262984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a506b45-5748-43c7-b9b4-33eb887f46a4 · outbound

This paper cites SDAR: A synergistic diffusion-autoregression paradigm for scalable sequence generation.arXiv preprint arXiv:2510.06303, 2025.

Thinking with Anchors: Grounded and Efficient Document Reasoning SDAR: A synergistic diffusion-autoregression paradigm for scalable sequence generation.arXiv preprint arXiv:2510.06303, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.348761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dca52eb-1408-4797-bab4-6b0762f268f3 · outbound

This paper cites Diachronic Document Dataset for Semantic Layout Analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning Diachronic Document Dataset for Semantic Layout Analysis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.478969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee3bbd3d-77a1-44c4-bc5b-5248a3b56d0c · outbound

This paper cites Molmo and pixmo: Open weights and open data for state-of- the-art vision-language models.

Thinking with Anchors: Grounded and Efficient Document Reasoning Molmo and pixmo: Open weights and open data for state-of- the-art vision-language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.678461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc0bc2d-daf6-4fe0-acbe-d41226c90871 · outbound

This paper cites HoloCount: A Holistic Visual Counting Benchmark for MLLMs.

Thinking with Anchors: Grounded and Efficient Document Reasoning HoloCount: A Holistic Visual Counting Benchmark for MLLMs

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:24:55.761641Z

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 2fdd163c-3a6d-4f70-830e-8d288f4cb57d · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:49.934247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d869abe-5c80-455a-aa68-321478e61d8b · outbound

This paper cites YOLOX: Exceeding YOLO Series in 2021.

Thinking with Anchors: Grounded and Efficient Document Reasoning YOLOX: Exceeding YOLO Series in 2021

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.023097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f503460-1747-43d4-b41f-fc41ecfe8519 · outbound

This paper cites Better & faster large language models via multi-token prediction.

Thinking with Anchors: Grounded and Efficient Document Reasoning Better & faster large language models via multi-token prediction

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.131818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d863bb68-d4ae-4d07-ae0b-474357c11d1f · outbound

This paper cites Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, and Tong Sun.

Thinking with Anchors: Grounded and Efficient Document Reasoning Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, and Tong Sun

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.211249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bf1e27a-3c7c-41db-a7b8-3332fbfef14c · outbound

This paper cites ADoPD: A large-scale document page decomposition dataset.

Thinking with Anchors: Grounded and Efficient Document Reasoning ADoPD: A large-scale document page decomposition dataset

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.284619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f9b4020-4b7a-4051-b975-a4c2e83b929a · outbound

This paper cites Visual programming: Compositional visual reasoning without training.

Thinking with Anchors: Grounded and Efficient Document Reasoning Visual programming: Compositional visual reasoning without training

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.339968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 411e90da-7263-4a79-b97e-a8d49deb4b08 · outbound

This paper cites DocAtlas: Multilingual Document Understanding Across 80+ Languages.

Thinking with Anchors: Grounded and Efficient Document Reasoning DocAtlas: Multilingual Document Understanding Across 80+ Languages

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:24:55.065353Z

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 de501bda-bfc5-4cd5-92a2-e5fdad6cf85e · outbound

This paper cites Drone-based object counting by spatially regularized regional proposal network.

Thinking with Anchors: Grounded and Efficient Document Reasoning Drone-based object counting by spatially regularized regional proposal network

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.590490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c32ed399-ba1a-4a3b-a62c-6f3c45762d92 · outbound

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

Thinking with Anchors: Grounded and Efficient Document Reasoning Layoutlmv3: Pre-training for document ai with unified text and image masking

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.674143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45afe1ac-cda1-4449-b81d-fe0632a77905 · outbound

This paper cites Composition loss for counting, density map estimation and localization in dense crowds.

Thinking with Anchors: Grounded and Efficient Document Reasoning Composition loss for counting, density map estimation and localization in dense crowds

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.779625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d65af17d-37ba-4d74-a156-8e4f031bbbdd · outbound

This paper cites OCR-free document understanding transformer.

Thinking with Anchors: Grounded and Efficient Document Reasoning OCR-free document understanding transformer

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:50.928068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896c4cc0-aa0e-4673-972f-6b9426b418c6 · outbound

This paper cites Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick.

Thinking with Anchors: Grounded and Efficient Document Reasoning Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:51.487779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88d80684-a1b8-4f5b-96b4-a410ad80ced4 · outbound

This paper cites Page segmentation using a convolutional neural network with trainable co-occurrence features.

Thinking with Anchors: Grounded and Efficient Document Reasoning Page segmentation using a convolutional neural network with trainable co-occurrence features

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:51.598760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f90620e-7413-4ee8-9718-02312095bd77 · outbound

This paper cites DocBank: A benchmark dataset for document layout analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning DocBank: A benchmark dataset for document layout analysis

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:51.860465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21620cec-624c-4959-9099-2cf26a4621dc · outbound

This paper cites Morariu, Handong Zhao, Rajiv Jain, Varun Manjunatha, and Hongfu Liu.

Thinking with Anchors: Grounded and Efficient Document Reasoning Morariu, Handong Zhao, Rajiv Jain, Varun Manjunatha, and Hongfu Liu

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:51.949260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820acda7-e2b4-4fa0-8336-abeae281e46f · outbound

This paper cites MonkeyOCR: Document parsing with a structure-recognition-relation triplet paradigm.arXiv preprint arXiv:2506.05218, 2025.

Thinking with Anchors: Grounded and Efficient Document Reasoning MonkeyOCR: Document parsing with a structure-recognition-relation triplet paradigm.arXiv preprint arXiv:2506.05218, 2025

Reference 34

Resolution: verified exact; doi, observed 2026-08-07T00:24:55.043880Z

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 77cd14d2-05c4-4874-b781-bdd45a5cdeed · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

Thinking with Anchors: Grounded and Efficient Document Reasoning Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.105752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4163009-e78c-427a-bae8-31c41caa1fc4 · outbound

This paper cites Visual instruction tuning.

Thinking with Anchors: Grounded and Efficient Document Reasoning Visual instruction tuning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.183456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43378107-26ca-4fa4-a554-6d8ab5ef90cc · outbound

This paper cites Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection.

Thinking with Anchors: Grounded and Efficient Document Reasoning Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.290243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5c1e1f-4a3a-4ab7-a795-8458df0ef21a · outbound

This paper cites Unified-IO 2: Scaling autoregressive multimodal models with vision, language, audio, and action.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unified-IO 2: Scaling autoregressive multimodal models with vision, language, audio, and action

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.374404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 394f9ca7-b8f4-4e03-81a5-0a8b81ea2f44 · outbound

This paper cites Thinking with visual primitives.

Thinking with Anchors: Grounded and Efficient Document Reasoning Thinking with visual primitives

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.470880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac83a38-d9a9-40b1-bf01-69180567a452 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.561322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61bccc2-bb04-4df5-9e9e-1886828ffa9a · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 41

Resolution: verified exact; doi, observed 2026-08-07T00:24:54.960277Z

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 61f184af-d016-4a8e-b440-6610a124707a · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 42

Resolution: verified exact; doi, observed 2026-08-07T00:24:54.952861Z

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 a9b12337-80b2-4e52-a59f-e6f44547cc9e · outbound

This paper cites Iiit-ar-13k: a new dataset for graphical object detection in documents.

Thinking with Anchors: Grounded and Efficient Document Reasoning Iiit-ar-13k: a new dataset for graphical object detection in documents

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:52.824268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6ae49ec-c851-4144-9fb7-a10bfc31b88a · outbound

This paper cites IndicDLP: A foundational dataset for multi-lingual and multi-domain document layout parsing.

Thinking with Anchors: Grounded and Efficient Document Reasoning IndicDLP: A foundational dataset for multi-lingual and multi-domain document layout parsing

Reference 44

Resolution: verified exact; doi, observed 2026-08-07T00:24:54.944986Z

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 41a110d7-a2a8-43ae-aac8-b3c346f3a1cf · outbound

This paper cites Large Language Diffusion Models.

Thinking with Anchors: Grounded and Efficient Document Reasoning Large Language Diffusion Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.065685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7201835-c1b5-4f7e-b8d9-8f9a55eefb83 · outbound

This paper cites A general approach for multi-oriented text line extraction of handwritten documents.IJDAR, 2012.

Thinking with Anchors: Grounded and Efficient Document Reasoning A general approach for multi-oriented text line extraction of handwritten documents.IJDAR, 2012

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.158010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 808f3734-c002-475a-a11d-5faf1cca39c0 · outbound

This paper cites Teaching clip to count to ten.

Thinking with Anchors: Grounded and Efficient Document Reasoning Teaching clip to count to ten

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.219257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58608b4b-dc55-4974-b221-e0d013a8ec6f · outbound

This paper cites Continuous document layout analysis: Human-in-the-loop AI-based data curation, database, and evaluation in the domain of public affairs.Information Fusion, 108:102398, 2024.

Thinking with Anchors: Grounded and Efficient Document Reasoning Continuous document layout analysis: Human-in-the-loop AI-based data curation, database, and evaluation in the domain of public affairs.Information Fusion, 108:102398, 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.369671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dc67f54-36c3-4482-8fda-d13e60af90e2 · outbound

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

Thinking with Anchors: Grounded and Efficient Document Reasoning Kosmos-2: Grounding Multimodal Large Language Models to the World

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.495972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7faada0d-29b7-45e0-b275-7ae08b53f293 · outbound

This paper cites Nassar, and Peter W.

Thinking with Anchors: Grounded and Efficient Document Reasoning Nassar, and Peter W

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.740933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 276ccffa-1798-4196-9fd5-131ebe9d0330 · outbound

This paper cites Learning to count everything.

Thinking with Anchors: Grounded and Efficient Document Reasoning Learning to count everything

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.802744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec3cda0e-375b-44a3-b16c-aa0c366f0ed1 · outbound

This paper cites SAM 2: Segment Anything in Images and Videos.

Thinking with Anchors: Grounded and Efficient Document Reasoning SAM 2: Segment Anything in Images and Videos

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:53.950122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01ed7edc-18a5-474a-8a50-c52288b54ea3 · outbound

This paper cites RF-DETR: Neural architecture search for real-time detection transformers.

Thinking with Anchors: Grounded and Efficient Document Reasoning RF-DETR: Neural architecture search for real-time detection transformers

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.060348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 034e7500-57ea-46a7-a51d-dff8000ef3ad · outbound

This paper cites Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method.IEEE transactions on pattern analysis and machine intelligence, 44(5):2594–2609, 2020.

Thinking with Anchors: Grounded and Efficient Document Reasoning Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method.IEEE transactions on pattern analysis and machine intelligence, 44(5):2594–2609, 2020

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.342985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 193b4e5c-ae56-4c2f-8b9a-1134a1f869f3 · outbound

This paper cites An overview of the tesseract OCR engine.

Thinking with Anchors: Grounded and Efficient Document Reasoning An overview of the tesseract OCR engine

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.438755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f80cc12e-ffea-4cfc-a0ac-e5ff2cf213ab · outbound

This paper cites ViperGPT: Visual inference via python execution for reasoning.

Thinking with Anchors: Grounded and Efficient Document Reasoning ViperGPT: Visual inference via python execution for reasoning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.441343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d90caa-d664-49e6-8f4a-30ba8a1e5e0a · outbound

This paper cites CountQA: How Well Do MLLMs Count in the Wild?.

Thinking with Anchors: Grounded and Efficient Document Reasoning CountQA: How Well Do MLLMs Count in the Wild?

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.443710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5576bf1c-6c8e-4710-9832-12241c09914a · outbound

This paper cites Unifying vision, text, and layout for universal document processing.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unifying vision, text, and layout for universal document processing

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.446460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30ce183f-53e3-4d55-b75e-a072d5c21aeb · outbound

This paper cites Kwai Keye-VL-2.0 Technical Report.

Thinking with Anchors: Grounded and Efficient Document Reasoning Kwai Keye-VL-2.0 Technical Report

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:24:55.321032Z

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 819bd54a-be10-4975-be9c-c34d5d50c113 · outbound

This paper cites YOLOv12: Attention-Centric Real-Time Object Detectors.

Thinking with Anchors: Grounded and Efficient Document Reasoning YOLOv12: Attention-Centric Real-Time Object Detectors

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.451586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfe4410f-5234-4672-8b85-2a1f5e692804 · outbound

This paper cites Tjong Kim Sang and Fien De Meulder.

Thinking with Anchors: Grounded and Efficient Document Reasoning Tjong Kim Sang and Fien De Meulder

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.454053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb24a83c-1134-40de-b4b8-8d44b04c9ae9 · outbound

This paper cites SCAN: Semantic document layout analysis for textual and visual retrieval-augmented generation.

Thinking with Anchors: Grounded and Efficient Document Reasoning SCAN: Semantic document layout analysis for textual and visual retrieval-augmented generation

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.456515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9698d5c8-eaaa-4402-9ca6-0ebb4acd8e55 · outbound

This paper cites Nwpu-crowd: A large-scale benchmark for crowd counting and localization.IEEE transactions on pattern analysis and machine intelligence, 43(6):2141–2149, 2020.

Thinking with Anchors: Grounded and Efficient Document Reasoning Nwpu-crowd: A large-scale benchmark for crowd counting and localization.IEEE transactions on pattern analysis and machine intelligence, 43(6):2141–2149, 2020

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.459129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4259258c-d8c4-42b8-ae2a-de5784bd6c20 · outbound

This paper cites LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding.

Thinking with Anchors: Grounded and Efficient Document Reasoning LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.461437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a690aa5d-53aa-4c4e-8ebe-a2afa9f8a5b6 · outbound

This paper cites Fast-dLLM v2: Efficient block-diffusion LLM.arXiv preprint arXiv:2509.26328, 2025.

Thinking with Anchors: Grounded and Efficient Document Reasoning Fast-dLLM v2: Efficient block-diffusion LLM.arXiv preprint arXiv:2509.26328, 2025

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.463953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8fe4277-dccc-47ee-9532-5d1ffebcd9a8 · outbound

This paper cites DocGenome: An open large-scale scientific document benchmark for training and testing multi-modal large language models.arXiv preprint arXiv:2406.11633, 2024.

Thinking with Anchors: Grounded and Efficient Document Reasoning DocGenome: An open large-scale scientific document benchmark for training and testing multi-modal large language models.arXiv preprint arXiv:2406.11633, 2024

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.466365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cbf61c2-a4cd-4e7c-8e59-d77d14e2081e · outbound

This paper cites Florence-2: Advancing a unified representation for a variety of vision tasks.

Thinking with Anchors: Grounded and Efficient Document Reasoning Florence-2: Advancing a unified representation for a variety of vision tasks

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.469000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 585d1668-23e4-4831-8573-b8abb2c1dced · outbound

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

Thinking with Anchors: Grounded and Efficient Document Reasoning Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.471478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fec97968-127e-4f4a-9bcb-371692c94886 · outbound

This paper cites MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action.

Thinking with Anchors: Grounded and Efficient Document Reasoning MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.474041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712c21a6-6553-49b6-b733-ed53f314de63 · outbound

This paper cites Dream 7B: Diffusion Large Language Models.

Thinking with Anchors: Grounded and Efficient Document Reasoning Dream 7B: Diffusion Large Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.476459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8554b5dd-8a74-4452-806c-39494a6757ed · outbound

This paper cites Ferret: Refer and ground anything anywhere at any granularity.

Thinking with Anchors: Grounded and Efficient Document Reasoning Ferret: Refer and ground anything anywhere at any granularity

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.479375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32fc71cf-f639-4ea2-b614-8097c6899d45 · outbound

This paper cites Single-image crowd counting via multi- column convolutional neural network.

Thinking with Anchors: Grounded and Efficient Document Reasoning Single-image crowd counting via multi- column convolutional neural network

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.481841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ddfc482-a3c7-4627-a6b0-b25ba5d6ace0 · outbound

This paper cites Multimodal Chain-of-Thought Reasoning in Language Models.

Thinking with Anchors: Grounded and Efficient Document Reasoning Multimodal Chain-of-Thought Reasoning in Language Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.484326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76f1fca5-d39d-40bf-9c35-fe62fe81cd9c · outbound

This paper cites DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception.

Thinking with Anchors: Grounded and Efficient Document Reasoning DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.487012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 747ef930-a335-48d1-9ef0-b22531f0f2e4 · outbound

This paper cites PubLayNet: Largest dataset ever for document layout analysis.

Thinking with Anchors: Grounded and Efficient Document Reasoning PubLayNet: Largest dataset ever for document layout analysis

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.495171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21be752e-a656-41b4-a9a0-f5dcd312670d · outbound

This paper cites DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception.

Thinking with Anchors: Grounded and Efficient Document Reasoning DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.489763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c82c4cec-adf2-442f-9f4c-917c7ff3c3f9 · outbound

This paper cites FLARE: Diffusion for Hybrid Language Model.

Thinking with Anchors: Grounded and Efficient Document Reasoning FLARE: Diffusion for Hybrid Language Model

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:24:55.094129Z

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 f7059b72-769a-400f-b7a3-777ceee1a682 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.500735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee60e37-69df-4e82-8e5a-05747ca7b8c8 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.502944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9f39d7c-2bdb-4680-a610-450e85432332 · outbound

This paper cites icon.A single large, visually striking standalone graphic =prominent pattern.

Thinking with Anchors: Grounded and Efficient Document Reasoning icon.A single large, visually striking standalone graphic =prominent pattern

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.505710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17df3003-ab72-472a-a9db-0c63384e8bf6 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.508595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503edb93-da53-495b-a3d4-2d42f43aeaad · outbound

This paper cites Image labels beside photos =image caption.

Thinking with Anchors: Grounded and Efficient Document Reasoning Image labels beside photos =image caption

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.511061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82e2858e-b7ac-4263-9c57-333f08db9b7e · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.513793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca508761-afb6-4de2-bb94-4878bf0ee620 · outbound

This paper cites Plain colored region without border =color block (borderless).

Thinking with Anchors: Grounded and Efficient Document Reasoning Plain colored region without border =color block (borderless)

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.516548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38ebcd4d-8e19-4d28-b7cb-4fc0cb202e2a · outbound

This paper cites Do not split the tag across modes.

Thinking with Anchors: Grounded and Efficient Document Reasoning Do not split the tag across modes

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.519071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc58f7d-9a72-4852-bf8d-5cc4757c8de8 · outbound

This paper cites A single-item list must still be separated.

Thinking with Anchors: Grounded and Efficient Document Reasoning A single-item list must still be separated

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.521947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b985886-c44d-4bda-bac1-a6238c1db247 · outbound

This paper cites background pattern vs.

Thinking with Anchors: Grounded and Efficient Document Reasoning background pattern vs

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.524518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 535cc545-2d32-426c-8d08-a2589687bb4d · outbound

This paper cites In newspaper layouts, side-column text adjacent to the main article =note; text at the very bottom =footer.

Thinking with Anchors: Grounded and Efficient Document Reasoning In newspaper layouts, side-column text adjacent to the main article =note; text at the very bottom =footer

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.527533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 930a991c-7147-4889-b10d-a2062b957a0c · outbound

This paper cites Hyperlinks or emphasis embedded in a large body-text block without their own pre-annotation belong to the body-text box.

Thinking with Anchors: Grounded and Efficient Document Reasoning Hyperlinks or emphasis embedded in a large body-text block without their own pre-annotation belong to the body-text box

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.530207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 071559b1-af95-4ebc-8c21-30641c358209 · outbound

This paper cites image caption; table title.Contextual explanatory text at the top-left or bottom of an image block =note.

Thinking with Anchors: Grounded and Efficient Document Reasoning image caption; table title.Contextual explanatory text at the top-left or bottom of an image block =note

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.533010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e6aefdc-f807-48f2-aeca-48b92022a575 · outbound

This paper cites note.A label directly beside or below a photo =image caption.

Thinking with Anchors: Grounded and Efficient Document Reasoning note.A label directly beside or below a photo =image caption

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.535664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7007ce9d-855c-441b-a333-faaba021672f · outbound

This paper cites All elements above =foreground.

Thinking with Anchors: Grounded and Efficient Document Reasoning All elements above =foreground

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.538174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c12e59c-14f2-4ab7-9c3a-81f16d34e805 · outbound

This paper cites prominent pattern; legend vs.

Thinking with Anchors: Grounded and Efficient Document Reasoning prominent pattern; legend vs

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.541019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1317472c-6ea6-4b84-ae68-ffce08e77bcc · outbound

This paper cites legend.Text directly below a photo pointing to it =image caption.

Thinking with Anchors: Grounded and Efficient Document Reasoning legend.Text directly below a photo pointing to it =image caption

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.543430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adde57ab-746f-41cf-8661-9033fa4c138c · outbound

This paper cites icon (cartoons).Cartoon resembling a recognizable icon-style symbol =icon.

Thinking with Anchors: Grounded and Efficient Document Reasoning icon (cartoons).Cartoon resembling a recognizable icon-style symbol =icon

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.546004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ddeea5b-46e3-415f-ac43-68fe1e9ee029 · outbound

This paper cites background pattern (full-bleed non-solid).If the bottommost layer is a non-solid graphic spanning the full width or height, label itbackground image, notbackground pattern.

Thinking with Anchors: Grounded and Efficient Document Reasoning background pattern (full-bleed non-solid).If the bottommost layer is a non-solid graphic spanning the full width or height, label itbackground image, notbackground pattern

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.550266Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db1aa9a-c987-4752-a436-e52149246554 · outbound

This paper cites There areNnumbered boxes (0..N−1). Group them.

Thinking with Anchors: Grounded and Efficient Document Reasoning There areNnumbered boxes (0..N−1). Group them

Reference 101

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.553670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8876943-0b61-419d-a001-4362a52b0c31 · outbound

This paper cites Below them on the right,[[6]] marks the First in Malaysia badge.

Thinking with Anchors: Grounded and Efficient Document Reasoning Below them on the right,[[6]] marks the First in Malaysia badge

Reference 103

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.559316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 207ec647-6593-4c59-b01b-4cb8071ff591 · outbound

This paper cites 37 Fine-grained Counting [Trigger_Placeholder] How many regions on this page should be counted as Photograph? Original Image Image with Visual Anchors Anchor Thinking Reasoning.

Thinking with Anchors: Grounded and Efficient Document Reasoning 37 Fine-grained Counting [Trigger_Placeholder] How many regions on this page should be counted as Photograph? Original Image Image with Visual Anchors Anchor Thinking Reasoning

Reference 104

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.562342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a823d827-ad93-4d7a-acc8-a393b4288557 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 106

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.567489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 431c2b81-32ef-45ca-b5ec-52ebf4941ca4 · outbound

This paper cites 38 Fine-grained Counting [Trigger_Placeholder] Count the Table regions visible on this page.

Thinking with Anchors: Grounded and Efficient Document Reasoning 38 Fine-grained Counting [Trigger_Placeholder] Count the Table regions visible on this page

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.570262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc25a1f-2411-43ac-be70-2b6d5cb20636 · outbound

This paper cites an unresolved cited work.

Thinking with Anchors: Grounded and Efficient Document Reasoning Unresolved cited work

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-07T00:24:54.575516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers