5 papers
A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends
Yihao Ding, Siwen Luo, Yue Dai +6
Visually Rich Document Understanding (VRDU) has become a pivotal area of research, driven by the need to automatically interpret documents that contain intricate visual, textual, a…
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…
SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction
Yihao Ding, Soyeon Caren Han, Yanbei Jiang +3
Domain-specific Visually Rich Document Understanding (VRDU) presents significant challenges due to the complexity and sensitivity of documents in fields such as medicine, finance,…
Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering
Zechuan Li, Hongshan Yu, Yihao Ding +3
3D Scene Question Answering (3D SQA) represents an interdisciplinary task that integrates 3D visual perception and natural language processing, empowering intelligent agents to com…
A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
Yan Li, Tianyi Zhang, Zechuan Li +1
Transformer-based Large Language Models (LLMs) struggle with inputs exceeding their training context window due to positional out-of-distribution (O.O.D.) issues that disrupt atten…