🤖 Advanced OCR

Neural Recognition, Document AI, Layout Analysis, Multi-modal Processing

Generalizing Vision-Language Models to Novel Domains: A Comprehensive Survey
arxiv.org·1d
📊Learned Metrics
Computer-vision research powers surveillance technology
nature.com·7h·
Discuss: Hacker News
🔎OSINT Techniques
Powering Smarter AI with Precision — Image Data Annotation at AkbhcodeAI
dev.to·1d·
Discuss: DEV
🤖AI Paleography
Building an ML model to generate fonts
fontweaver.com·1d·
Discuss: Hacker News
🔠Terminal Fonts
Kumo Surfaces Structured Data Patterns Generative AI Misses
thenewstack.io·9h
📊Graph Databases
Unfolding the Past: A Comprehensive Deep Learning Approach to Analyzing Incunabula Pages
arxiv.org·1d
🤖Manuscript AI
How to Prove That An Email Was Received
metaspike.com·3h
📄Document Digitization
Google's Imagen 4 text-to-image model promises 'significantly improved' boring images
engadget.com·12h
📸TIFF Evolution
AMF-MedIT: An Efficient Align-Modulation-Fusion Framework for Medical Image-Tabular Data
arxiv.org·19h
🧠Machine Learning
Why Your Next LLM Might Not Have A Tokenizer
towardsdatascience.com·1d
🤖Grammar Induction
Show HN: Turn Images and Text into AI Videos in Minutes
imagetovideo.io·9h·
Discuss: Hacker News
🎥Streaming Codecs
An All-Around Better Horse
patrickhebron.com·6h·
Discuss: Hacker News
🧠Knowledge Management
DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts
arxiv.org·19h
🧠Machine Learning
Show HN: TableSprint- Supabase alternative with vibe coding features
tablesprint.com·20h·
Discuss: Hacker News
📲Digitization
From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge
arxiv.org·1d
⟷Bidirectional Programming
Unlocking Hyper-Security: The Power of AI in Multi-Modal Biometric Systems
dev.to·19h·
Discuss: DEV
🎵Spectral Hashing
ReMAR-DS: Recalibrated Feature Learning for Metal Artifact Reduction and CT Domain Transformation
arxiv.org·19h
📊Learned Metrics
A Deep Convolutional Neural Network-Based Novel Class Balancing for Imbalance Data Segmentation
arxiv.org·1d
🧠Machine Learning
10 FREE AI Tools That’ll Save You 10+ Hours a Week
kdnuggets.com·11h
🎙️Whisper
Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network
arxiv.org·19h
🌀Differential Geometry