Hao Feng
- Papers
- 11
Cite
Notes
Only stored in your browser.
Authored papers
11TextPecker: Rewarding Structural Anomaly Quantification for Enhancing Visual Text Rendering
arXiv 2026
Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting
arXiv 2025
OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
arXiv 2024
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering
arXiv 2024
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
arXiv 2024
AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding
arXiv 2024
DeepEraser: Deep Iterative Context Mining for Generic Text Eraser
arXiv 2024
TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding
arXiv 2024
Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs
arXiv 2023
Geometric Representation Learning for Document Image Rectification
arXiv 2022
DocScanner: Robust Document Image Rectification with Progressive Learning
arXiv 2021
Affiliations
Frequent co-authors
10from 11 papers