WildTab: Decoupling Content and Structure for Robust Multimodal Table Understanding in the Wild
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 6795-6804
Abstract
No abstract availableFunding Information
- CAAI-Tencent Rhino-Bird Open Research Fund (\/)
- National Natural Science Foundation of China (62376266)
- National Natural Science Foundation of China (62406318)
This publication has 19 references indexed in Scilit:
- TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token FocusingProceedings of the AAAI Conference on Artificial Intelligence, 2026
- SynTab-LLaVA: Enhancing Multimodal Table Understanding with Decoupled Synthesis2025
- DocVLM: Make Your VLM an Efficient Reader2025
- Honeybee: Locality-Enhanced Projector for Multimodal LLM2024
- Document Shadow Removal with Foreground Detection Learning From Fully Synthetic Images2022
- TSRFormer2022
- Parsing Table Structures in the Wild2021
- Exploring Simple Siamese Representation Learning2021
- DocUNet: Document Image Unwarping via a Stacked U-Net2018
- Describing Textures in the Wild2014