Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 43
Ozgur Ugurlu
ozgurugurlu
AI & ML interests
Natural Language Processing & Computational Linguistics
Recent Activity
liked a model 5 days ago
ResembleAI/Dramabox upvoted a paper 2 months ago
Multimodal OCR: Parse Anything from Documents liked a model 2 months ago
fishaudio/s2-proOrganizations
upvoted a paper 2 months ago
upvoted 4
papers 5 months ago
Can LLMs Estimate Student Struggles? Human-AI Difficulty Alignment with Proficiency Simulation for Item Difficulty Prediction
Paper • 2512.18880 • Published • 25
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
Paper • 2512.16676 • Published • 222
SAM 3: Segment Anything with Concepts
Paper • 2511.16719 • Published • 135
Agent READMEs: An Empirical Study of Context Files for Agentic Coding
Paper • 2511.12884 • Published • 28