Unlimited OCR Works
Paper • 2606.23050 • Published • 73
Hunter Heidenreich
hheiden-bevaya
AI & ML interests
None yet
Recent Activity
updated a model 12 days ago
hheiden-bevaya/gutenocr-3b-a10g-compile-cache published a model 12 days ago
hheiden-bevaya/gutenocr-3b-a10g-compile-cache upvoted a paper 23 days ago
Unlimited OCR WorksOrganizations
upvoted 13
papers 23 days ago
LLaVA-UHD v4: What Makes Efficient Visual Encoding in MLLMs?
Paper • 2605.08985 • Published • 24
Falcon Perception
Paper • 2603.27365 • Published • 17
Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement
Paper • 2603.22187 • Published • 1
Multimodal OCR: Parse Anything from Documents
Paper • 2603.13032 • Published • 46
DeepSeek-OCR 2: Visual Causal Flow
Paper • 2601.20552 • Published • 73
Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting
Paper • 2602.05384 • Published • 1
FireRed-OCR Technical Report
Paper • 2603.01840 • Published • 7
GLM-OCR Technical Report
Paper • 2603.10910 • Published • 10
LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
Paper • 2601.14251 • Published • 31
The Character Error Vector: Decomposable errors for page-level OCR evaluation
Paper • 2604.06160 • Published • 1
Training Long-Context Vision-Language Models Effectively with Generalization Beyond 128K Context
Paper • 2605.13831 • Published • 90
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training
Paper • 2606.03264 • Published • 27
upvoted a paper 24 days ago
upvoted a paper 4 months ago
upvoted 3
papers 6 months ago
upvoted 2
collections 6 months ago