🤖 Advanced OCR

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

Show HN: I built an SDK for building an AI RAG app with Supabase and pgvector
github.com·1d·
Discuss: Hacker News
🌀Brotli Internals
Over 30 AI models have been trained at 10^25 FLOP or greater
epoch.ai·1d·
Discuss: Hacker News
⚡Performance Mythology
All AI Models Might be The Same
blog.jxmo.io·4h·
Discuss: Hacker News
🧠Machine Learning
A Minimal DDPM
github.com·1d·
Discuss: Hacker News
🧠Machine Learning
GATE: Graph Attention Neural Networks with Real-Time Edge Construction for Robust Indoor Localization using Mobile Embedded Devices
arxiv.org·1d
🌀Riemannian Computing
FADE: Adversarial Concept Erasure in Flow Models
arxiv.org·18h
📊Rate-Distortion Theory
Are Vision Foundation Models Ready for Out-of-the-Box Medical Image Registration?
arxiv.org·18h
🌀Differential Geometry
RefSTAR: Blind Facial Image Restoration with Reference Selection, Transfer, and Reconstruction
arxiv.org·2d
📊Learned Metrics
Continuous Spiking Graph Neural Networks
arxiv.org·2d
🕸️Graph Embeddings
Women Sport Actions Dataset for Visual Classification Using Small Scale Training Data
arxiv.org·1d
📊Learned Metrics
SurgeryLSTM: A Time-Aware Neural Model for Accurate and Explainable Length of Stay Prediction After Spine Surgery
arxiv.org·18h
🧠Machine Learning
Representation learning with a transformer by contrastive learning for money laundering detection
arxiv.org·2d
🧠Machine Learning
Graph Representations for Reading Comprehension Analysis using Large Language Model and Eye-Tracking Biomarker
arxiv.org·18h
🧠Intelligence Compression
ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models
arxiv.org·2d
🧠Neural Compression
Artificial Finance: How AI Thinks About Money
arxiv.org·1d·
Discuss: Hacker News
🔲Cellular Automata
PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification
arxiv.org·1d
💻Local LLMs
MediaMind AI - Intelligent Content Discovery Platform with Algolia MCP Server
dev.to·1d·
Discuss: DEV
🧭Content Discovery
Static or Temporal? Semantic Scene Simplification to Aid Wayfinding in Immersive Simulations of Bionic Vision
arxiv.org·1d
✋Tactile Computing
SIEVE: Effective Filtered Vector Search with Collection of Indexes
arxiv.org·18h
🗂️Vector Databases
🤖 Build Your Own AI Assistant with LLMs
dev.to·6h·
Discuss: DEV
🎙️Whisper