🤖 Advanced OCR

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

Experimenting with Apple’s AI models inside Shortcuts
sixcolors.com·3h
⚡Proof Automation
MambaOutRS: A Hybrid CNN-Fourier Architecture for Remote Sensing Image Classification
arxiv.org·15h
🌀Riemannian Computing
Portable Network Graphics (PNG) Specification (Third Edition)
w3.org·22h·
Discuss: Hacker News
🕸️WebP Analysis
Multimodal Political Bias Identification and Neutralization
arxiv.org·1d
📄Text Segmentation
MemeMind: A Large-Scale Multimodal Dataset with Chain-of-Thought Reasoning for Harmful Meme Detection
arxiv.org·15h
🧮Vector Embeddings
Meta's V-JEPA 2 Aims to Redefine AI's Spatial Reasoning Without Video Data
gazeon.site·2h·
Discuss: Hacker News
🔲Cellular Automata
V2T-CoT: From Vision to Text Chain-of-Thought for Medical Reasoning and Diagnosis
arxiv.org·15h
🏛Digital humanities
Depict: AI-powered search for Indian museum artworks using CLIP embeddings
github.com·3d·
Discuss: Hacker News
📸TIFF Archaeology
Recurrent Visual Feature Extraction and Stereo Attentions for CT Report Generation
arxiv.org·15h
📄Document Streaming
Contextualizing SUTRA: Advancements in Multilingual & Efficient LLMs
hackernoon.com·3h
💻Local LLMs
StainPIDR: A Pathological Image Decouplingand Reconstruction Method for StainNormalization Based on Color VectorQuantization and Structure Restaining
arxiv.org·1d
📄OCR
Google/Videoprism
huggingface.co·20h·
Discuss: Hacker News
📊Learned Metrics
Scaffolding Dexterous Manipulation with Vision-Language Models
arxiv.org·15h
🤖Tape Automation
NAADA: A Noise-Aware Attention Denoising Autoencoder for Dental Panoramic Radiographs
arxiv.org·15h
🧠Machine Learning
Semantic Scene Graph for Ultrasound Image Explanation and Scanning Guidance
arxiv.org·15h
📝Document Chunking
Oblique Strategies for Vibe Coding
useyourexperience.com·1d·
Discuss: Hacker News
🇸🇪Nordic Algorithms
Which Vision Language Models Should You Use for Your Apps
thenewstack.io·2d
🗂️Vector Databases
Using Wavelets and Clustering to Predict Odd or Even Numbers: An Overengineered Approach with Pretty (But Confusing) Plots
dev.to·5h·
Discuss: DEV
🧠Machine Learning
GLIMPSE: Gradient-Layer Importance Mapping for Prompted Visual Saliency Explanation for Generative LVLMs
arxiv.org·15h
📊Learned Metrics
The Art of Deception: Understanding Generative Adversarial Networks (GANs)
dev.to·16h·
Discuss: DEV
🧠Neural Compression