📄 Document AI

Transformer Models, Layout Analysis, OCR Enhancement, Information Extraction

AIOps - A Multifaceted Challenge
blog.raymond.burkholder.net·19h
🦋Format Evolution
Show HN: I built a mobile app to help you read in a foreign language with LLMs
apps.apple.com·17h·
Discuss: Hacker News
🌳Context free grammars
AI Can Make You Laugh. But Can It Ever Be Truly Humorous?
undark.org·1d·
Discuss: Hacker News
⚡Proof Automation
Vitalik Buterin's response to AI 2027
vitalik.eth.limo·8h·
Discuss: Hacker News
🔲Cellular Automata
A Practical Comparison of AI Coding Agents
jaredforsyth.com·16h·
Discuss: Hacker News
🔐Capability Systems
Reliable by Design: Fast, Fail-Safe AI Agents
aimon.ai·16h·
Discuss: Hacker News
🔍Concolic Testing
Signs of the Past, Patterns of the Present: On the Automatic Classification of Old Babylonian Cuneiform Signs
arxiv.org·1d
🤖Paleographic ML
Explainable Collaborative Problem Solving Diagnosis with BERT using SHAP and its Implications for Teacher Adoption
arxiv.org·9h
🔍Type Inference
CrewAI meets RAG: built-in and custom solutions
dev.to·2d·
Discuss: DEV
⚡Proof Automation
SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation
arxiv.org·1d
📋Document Grammar
Self-Supervised Distillation of Legacy Rule-Based Methods for Enhanced EEG-Based Decision-Making
arxiv.org·9h
🧠Neural Codecs
How I keep up with AI research
thijsverreck.com·22h·
Discuss: Hacker News
🧭Content Discovery
IConMark: Robust Interpretable Concept-Based Watermark For AI Images
arxiv.org·1d
💧Digital Watermarking
The Power of HTML - Part 20: AI-Generated HTML: Tools and Best Practices
dev.to·2d·
Discuss: DEV
⚡Proof Automation
The calculus of variations of the Transformer on the hyperspherical tangent bundle
arxiv.org·9h
🌀Differential Geometry
How to Build a Full AI Workflow Without Code or APIs
dev.to·2h·
Discuss: DEV
⚔️Lean Tactics
DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning
arxiv.org·9h
📊Quantization
How AI Chatbots Are Transforming Customer Support in 2025
dev.to·6h·
Discuss: DEV
🎙️Whisper
Surfacing Variations to Calibrate Perceived Reliability of MLLM-generated Image Descriptions
arxiv.org·9h
⟷Bidirectional Programming
From Semantics, Scene to Instance-awareness: Distilling Foundation Model for Open-vocabulary Situation Recognition
arxiv.org·9h
🎙️Whisper