Program

Poster Session (14:00 – 15:30)

Workshop Papers

1. A Human-Annotated Reference Corpus for Medication Information Extraction from MIMIC-IV Discharge Summaries
   Provia Kadusabe, Abhishek Kaushik and Fiona Lawless
   Presenter: Provia Kadusabe
2. The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models
   Christoph Marjan Markus Walser, Mauricio Fadel Argerich and Jonathan Fürst
   Presenter: Jonathan Fürst
3. Splitting Documents at Lower Cost: Multi-Split Boundary Decisions for LLM-Based Page Stream Segmentation
   Nikhil Reddy Pottanigari, Sepideh Kharaghani, Saverio Vadacchino, Alejandro Posada and Ying Zhang
   Presenter: Nikhil Reddy Pottanigari
4. Text, Pixels, or Both? Evaluating Input Representations for Multimodal Document QA
   Nikhil Reddy Pottanigari, Sepideh Kharaghani, Saverio Vadacchino, Alejandro Posada, Kurt MacDonald and Ying Zhang
   Presenter: Nikhil Reddy Pottanigari
5. AdaptiveDocRAG: Efficient Document Understanding with Multimodal Large Language Models
   Surya Selvam and Anand Raghunathan
   Presenter: Surya Selvam (virtual)
6. Evidence-Guided Schema Normalization for Temporal Tabular Reasoning
   Ashish Thanga, Vibhu Dixit, Abhilash Shankarampeta and Vivek Gupta
   Presenter: Prasham Titiya
7. Most of a Document-VQA Score Is Answer Formatting
   Srinivas Harish
   Presenter: Srinivas Harish (virtual)
8. Graph-Guided Passage Retrieval for Author-Centric Structured Feedback
   Maitreya Prafulla Chitale, Ketaki Mangesh Shetye, Harshit Gupta, Manav Chaudhary, Manish Shrivastava and Vasudeva Varma
   Presenter: Maitreya Prafulla Chitale (virtual)
9. GraphER: An Efficient Graph-Based Enrichment and Reranking Method for Retrieval-Augmented Generation
   Ruizhong Miao, Yuying Wang, Rongguang Wang, Chenyang Li, Tao Sheng, Sujith Ravi and Dan Roth
   Presenter: Ruizhong Miao (virtual)
10. LongDA: Benchmarking LLM Agents for Long-Document Data Analysis
    Yiyang Li, Zheyuan Zhang, Tianyi Ma, Zehong Wang, Keerthiram Murugesan, Chuxu Zhang and Yanfang Ye
    Presenter: Yiyang Li (virtual)
11. Reflect and Retrieve: Multimodal Agentic Retrieval with Reflection and Query Agents for Document Search
    Tryambak Gangopadhyay, Md Sirajus Salekin, Yiyue Qian, Nkechinyere Nneka Agu, Shinan Zhang and Rinne Han
    Presenter: Tryambak Gangopadhyay (virtual)
12. LLMs and Reasoning in Health Insurance Policy Documents: A Dataset and Argument Graph Extraction Study
    Govind Arun, Sidharth N Krishna, Susie Xi Rao and Ajo Babu George
    Presenter: Govind Arun (virtual)
13. NutriChat: Evaluating Safety-Aware Retrieval-Augmented Generation for Nutrition Textbook Question Answering
    Hadis Ghafouri
    Presenter: Hadis Ghafouri (virtual)
14. Self-Study Reconsidered: The Hidden Fragility of Self-Generated QA Supervision
    Ekaterina Alimaskina, Denis Shveykin, Gleb Molodtsov, Shalygin Igor, Alexey Kadeishvili and Aleksandr Beznosikov
    Presenter: Gleb Molodtsov
15. The Fragility of Structured Context Access in Low-Bit LLMs
    Suren Kazarian, Ekaterina Alimaskina, Gleb Molodtsov and Aleksandr Beznosikov
    Presenter: Gleb Molodtsov
16. Measuring Artifact Reliance in Machine-Generated Text Detectors
    Anastasia Voznyuk and Andrey Grabovoy
    Presenter: Anastasia Voznyuk
17. Graph Retrieval in Multimodal RAG for Biomedical Documents: A Pharmacokinetics and Pharmacodynamics Case Study
    Primoz Kocbek, Katarina Meštrović, Nguyen Thu Huong, Ales Fajmut and Gregor Stiglic
    Presenter: Primoz Kocbek
18. Q-STR: Diagnosing Query-Driven Text-to-Table Reasoning in Cricket Narratives
    Ritam Upadhyay, Naman Ahuja, Rishabh Baral, Aparna Garimella and Vivek Gupta
    Presenter: Ritam Upadhyay (virtual)
19. Ontology-Guided Procedural Knowledge Extraction and Validation Case Study on the Lockout-Tagout Documents
    Cennet Oguz, Noon Pokaratsiri Goldstein, Jörg Steffen, Reetam Biswas and Günter Neumann
    Presenter: Noon Pokaratsiri Goldstein
20. Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents
    Yichao Jin, Yushuo Wang, Han Yuxuan, Ching Yee Sonia Kwan, Weiyang Song, Kent Chiu Jin Chun, Chong Hwee Wong, Tiong Kiat Wong, Kenneth Zhu Ke and Jingyuan Zhao
    Presenter: Yuxuan Han
21. What Transfers from a VLM Teacher? Comparing Supervision Signals for Visual Document Retrieval
    Saba Sturua and Han Xiao
    Presenter: Saba Sturua
22. Tabstructor: Reconstructing Latent Borders in Borderless and Partially Ruled Tables
    Alvin Sarraga Alon, Daniele De Rosa, Johannes Friedl and Riza Batista-Navarro
    Presenter: Alvin Sarraga Alon
23. Does the Interface Matter? Grounded Document QA in Interactive PDFs
    Eric S. Qiu and Joyce Gill
    Presenter: Joyce Gill
24. Silent Structured-Content Corruption in Document Parsing: A Span-Typed Diagnostic and a Released Cross-Parser Resource
    Ruiyang Zhang
    Presenter: Ruiyang Zhang (virtual)
25. CsPICO: A Unified Benchmark for Citation Screening in Systematic Reviews beyond Classification to Explain Exclusion Reasons
    Yewon Choi, Hyun Do Jung, Dain Ji, Hwiyoung Kim, Sungjun Kim and Jaehyung Kim
    Presenter: Yewon Choi
26. Sorry Robot, Happy Human: Vision-Language Models Read Only One of Two Legible Typographic Layers
    Mert İncidelen, Yamen Kashkash, Asya Berker and Murat Aydogan
    Presenter: Mert İncidelen
27. What Should Occupy the Context Budget? Latent Compression versus Budget-Matched Truncation in Document QA
    Artem Cherepanov and Albina Burlova
    Presenter: Albina Burlova
28. RAG Components Are Not Independently Rankable
    Vishnu Prasad Vijaya Kumar, Iaroslav Neverov, Pavel Chizhov, Anton Changalidis, Vaiva Kazanaviciute, Pierre-Carl Langlais, Anastasia Stasenko and Ivan P. Yamshchikov
    Presenter: Vishnu Prasad Vijaya Kumar
29. PDFPrime: Deterministic PDF Text Extraction Evaluated Against Fidelity-Measured References
    Shubhankit Singh and Aditya Jeevan Jethani
    Presenter: Shubhankit Singh (virtual)
30. LaTeXTrans Structure-Aware Translation of Complex LaTeX Documents
    Ziming Zhu, Chenglong Wang, Haosong Xu, Shunjie Xing, Yifu Huo, Fengning Tian, Quan Du, Di Yang, Chunliang Zhang, Tong Xiao and JingBo Zhu
    Presenter: Chenglong Wang
31. "Did You CoSeCh?": Faithfulness- and Coherence-Aware Auditing of Content Selection in Poster Generation
    Aaditya Deshpande, Savita Bhat and Shirish Karande
    Presenter: Aaditya Deshpande (virtual)
32. Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
    Nimrod Shabtay, Moshe Kimhi, Sivan Harary, Artem Spector, Ehud Rivlin, Chaim Baskin, Raja Giryes and Eli Schwartz
    Presenter: Moshe Kimhi (virtual)
33. DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
    Zhuchenyang Liu, Ziyi Wang, Yao Zhang and Yu Xiao
    Presenter: Zhuchenyang Liu
34. Comparative Study of AI Agent Architecture Efficiency in Table Processing Tasks
    Timur Gabbasov, Aleksandr Sandalov, Aleksandr Maksimov, Maria Khodorchenko and Nikolay Alekseevich Butakov
    Presenter: Timur Gabbasov
35. MaDOVE: a Dataset for Multilingual Document VQA Evaluation
    Elio Musacchio, Lucia Siciliani, Pierpaolo Basile, Giovanni Semeraro, Mark Federico Zampedroni and Asia Beatrice Uboldi
    Presenter: Elio Musacchio
36. Generating Edit-Inducing Questions for AI Research Manuscripts
    Sebastian Antony Joseph, Zichao Wang, Jennifer Healey, Alexa Siu, Junyi Jessy Li and Ani Nenkova
    Presenter: Sebastian Joseph (virtual)
37. Sieve and Sage: Efficient Distraction Filtering for Reliable RALM Abstention
    Jongbin Won, SungGeun AN and Jay-Yoon Lee
    Presenter: Jongbin Won
38. InSight-doc: Agentic Visual Perception for Long-Document Understanding
    Kaican Li, Weiyan Xie, Lewei Yao, Jiannan Wu, Lanqing Hong, Yongxiang Huang and Nevin L. Zhang
    Presenter: Kaican Li (virtual)
39. Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
    Sunah O and Jay-Yoon Lee
    Presenter: Sunah O

Shared Task Papers

1. Image Fidelity and VLM Ensemble for Expert-Level Single-Page Document Parsing on Dr.DocBench
   Yushuo Wang, Han Yuxuan, Yichao Jin, Kenneth Zhu Ke and Jingyuan Zhao
   Presenter: Yuxuan Han
2. Evidence Without Answers: Set-Difference Target Selection and a Label-Free Estimate of Answer Loss
   Chen-Jui Yu, Shui-Hsiang Hsu, Shao-Cheng Lu, Jui-Piao Chen, Shen Chih Hsuan, Chi-Hsun Tsai, Ru-Zhen Hou, Ping-Jung Shih, I-Chi Lee, Hsiang-Yi Yen, Ming-Der Yang and Yao-Chung Fan
   Presenter: Chen-Jui Yu
3. When the Evidence Is Right, the Math Is Easy: Understanding the Challenges of Document-Grounded Reasoning
   Aftab Hossain Mikat and Tamjid Hasan Fahim
   Presenter: Aftab Hossain Mikat (virtual)
4. Acessilia at Dr.DocBench 2026: Agentic Document Parsing through Canonical Tree Adjudication
   Marcelo Akira Inuzuka, Marcos Paulo C M Queiroz, Jhonata Fernandes Cordeiro and Eduardo Fraga Pereira
   Presenter: Marcelo Akira Inuzuka (virtual)
5. Evidence First, Arithmetic Second: A System Report and Failure Analysis for DOCSEM
   Divya Godara and Sachin Gupta
   Presenter: Sachin Gupta (virtual)
6. The Document Carries Its Own Answer Key: Elimination, Arbitration and Calibration for DocSEM
   Shui-Hsiang Hsu, Chen-Jui Yu, Shao-Cheng Lu, Jui-Piao Chen, Shen Chih Hsuan, Chi-Hsun Tsai, Ru-Zhen Hou, Ping-Jung Shih, I-Chi Lee, Hsiang-Yi Yen, Ming-Der Yang and Yao-Chung Fan
   Presenter: Shui-Hsiang Hsu
7. Retrieve, Reason, Verify: A Modular Multi-Model System for DocSem
   Pranavi Tadivalasa
   Presenter: Pranavi Tadivalasa (virtual)
8. A Cost-Efficient Vision-Text Cascade for Document QA: What Resolution Buys and What It Doesn't
   Urjita Bedekar
   Presenter: Urjita Bedekar
9. DFM at DocSEM 2026: Investigating a Guided-Reasoning Pipeline for Open Models Under a Validation-Test Shift
   Dyonnatan Ferreira Maia
   Presenter: Dyonnatan Ferreira Maia (virtual)