2 citations · 2 across the 9 of their papers we have counts for
9 papers
GUIDE: Guiding Internal Evidence with Language Instructions
Soyeon Caren Han, Hyunsuk Chung, Jinwoo Kim +2
Large multimodal models follow instructions about what to generate, but not necessarily about what evidence to rely on. Hence, models may continue to depend on shortcut-associated…
Physics-based phenomenological characterization of cross-modal bias in multimodal models
Hyeongmo Kim, Sohyun Kang, Yerin Choi +5
The term 'algorithmic fairness' is used to evaluate whether AI models operate fairly in both comparative (where fairness is understood as formal equality, such as "treat like cases…
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
Hyunsuk Chung, Soyeon Caren Han, Seungyeon Ji +3
Multimodal foundation models integrate heterogeneous signals across modalities, yet it remains unclear whether their predictions can be controlled by explicitly modulating reliance…
SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction
Yihao Ding, Soyeon Caren Han, Zechuan Li +1
Visually Rich Documents (VRDs), comprising elements such as charts, tables, and paragraphs, convey complex information across diverse domains. However, extracting key information f…
PEACH: Pretrained-embedding Explanation Across Contextual and Hierarchical Structure
Feiqi Cao, Caren Han, Hyunsuk Chung
In this work, we propose a novel tree-based explanation technique, PEACH (Pretrained-embedding Explanation Across Contextual and Hierarchical Structure), that can explain how text-…
PDFVQA: A New Dataset for Real-World VQA on PDF Documents
Yihao Ding, Siwen Luo, Hyunsuk Chung +1
Document-based Visual Question Answering examines the document understanding of document images in conditions of natural language questions. We proposed a new document-based VQA da…
Form-NLU: Dataset for the Form Natural Language Understanding
Yihao Ding, Siqu Long, Jiabin Huang +4
Compared to general document analysis tasks, form document structure understanding and retrieval are challenging. Form documents are typically made by two types of authors; A form…
PiggyBack: Pretrained Visual Question Answering Environment for Backing up Non-deep Learning Professionals
Zhihao Zhang, Siwen Luo, Junyi Chen +4
We propose a PiggyBack, a Visual Question Answering platform that allows users to apply the state-of-the-art visual-language pretrained models easily. The PiggyBack supports the fu…
V-Doc : Visual questions answers with Documents
Yihao Ding, Zhe Huang, Runlin Wang +5
We propose V-Doc, a question-answering tool using document images and PDF, mainly for researchers and general non-deep learning experts looking to generate, process, and understand…