📄 Document AI

Transformer Models, Layout Analysis, OCR Enhancement, Information Extraction

Meta: Slow Blogging Ahead
blog.dshr.org·8h·
Discuss: www.blogger.com
📜TEI Encoding
An evaluation scheme for sampling
statmodeling.stat.columbia.edu·4h
🧮Kolmogorov Bounds
Inference-Time Techniques for High-Quality, Low-Latency Speech Generation
blog.play.ai·1d·
Discuss: Hacker News
🎙️Whisper
Recursively self improving AI might not work without these functions
secondsight.dev·2d·
Discuss: Hacker News
🔲Cellular Automata
Why Your WYSIWYG Editor is a Critical Accessibility Tool
hackernoon.com·17h
📄PostScript
RAG Systems Are Breaking the Barriers of Language Models: Here's How
hackernoon.com·1d
💻Local LLMs
AI and the great digital agency unbundling
dri.es·1d·
Discuss: Lobsters, Hacker News
📚MARC Evolution
Machine Learning Fundamentals: gradient descent example
dev.to·6h·
Discuss: DEV
⚡Incremental Computation
Build a Fullstack Stock Portfolio Agent with LangGraph and AG-UI
dev.to·10h·
Discuss: DEV
📐Proof Assistants
How to build unified AI interfaces using the Vercel AI SDK
dev.to·5h·
Discuss: DEV
🎬WebCodecs API
CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigation
arxiv.org·19h
📐Projective Geometry
NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining
arxiv.org·3d
🤖Advanced OCR
Unlocking True Document Productivity with PixLab Vision Workspace
dev.to·3d·
Discuss: DEV
📄Document Digitization
Reinforcement Learning in hyperbolic space for multi-step reasoning
arxiv.org·19h
🌀Hyperbolic Geometry
MultiTaskDeltaNet: Change Detection-based Image Segmentation for Operando ETEM with Application to Carbon Gasification Kinetics
arxiv.org·1d
📄Document Digitization
Understanding Prompt Programming Tasks and Questions
arxiv.org·19h
🔗Concatenative Programming
TransLPRNet: Lite Vision-Language Network for Single/Dual-line Chinese License Plate Recognition
arxiv.org·19h
🤖Advanced OCR
AI reveals new details about a famous Latin inscription
sciencenews.org·1d·
Discuss: Hacker News
🤖AI Paleography
A tissue and cell-level annotated H&E and PD-L1 histopathology image dataset in non-small cell lung cancer
arxiv.org·19h
📲Digitization
Vision Transformer attention alignment with human visual perception in aesthetic object evaluation
arxiv.org·19h
📊Learned Metrics