Fine-Grained Detection of AI-Generated Text Using Sentence-Level Segmentation
arxiv.org·5h
📄Document AI
What is NLP? How Does it Work?
dev.to·1d·
Discuss: DEV
📝Text Parsing
Behavioral Validity Checks for ML‑Based "Coding"
gojiberries.io·3h·
Discuss: Hacker News
🧠Intelligence Compression
Emacs: Cycle through different paragraph formats: all on one line, wrapped, max one sentence per line, one sentence per line
sachachua.com·18h
📝Parsing Grammars
Open Political Corpora: Structuring, Searching, and Analyzing Political Text Collections with PoliCorp
arxiv.org·5h
📄Semantic Chunking
Accurate Thyroid Cancer Classification using a Novel Binary Pattern Driven Local Discrete Cosine Transform Descriptor
arxiv.org·5h
📄OCR
Real, Fake, or Manipulated? Detecting Machine-Influenced Text
arxiv.org·1d
🔤Character Classification
Domain-Adaptive Pre-Training for Arabic Aspect-Based Sentiment Analysis: A Comparative Study of Domain Adaptation and Fine-Tuning Strategies
arxiv.org·5h
🤖Grammar Induction
HARE: an entity and relation centric evaluation framework for histopathology reports
arxiv.org·5h
⚙️Compression Benchmarking
Graph Harmony: Harmonizing Global and Local Views for Superior Clustering
dev.to·1d·
Discuss: DEV
🌊Spectral Clustering
Extending Automatic Machine Translation Evaluation to Book-Length Documents
arxiv.org·5h
⚙️Compression Benchmarking
Why Tables Are the Hardest Problem in Document AI
runpulse.com·19h·
Discuss: Hacker News
📄Document AI
DragOSM: Extract Building Roofs and Footprints from Aerial Images by Aligning Historical Labels
arxiv.org·5h
🔶Voronoi Diagrams
DocIQ: A Benchmark Dataset and Feature Fusion Network for Document Image Quality Assessment
arxiv.org·5h
🤖Advanced OCR
Improving Zero-shot Sentence Decontextualisation with Content Selection and Planning
arxiv.org·5h
📄Text Chunking
GraDeT-HTR: A Resource-Efficient Bengali Handwritten Text Recognition System utilizing Grapheme-based Tokenizer and Decoder-only Transformer
arxiv.org·5h
🤖Advanced OCR
OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System
arxiv.org·5h
🎯Content Recommendation
CommonForms: A Large, Diverse Dataset for Form Field Detection
arxiv.org·5h
📄PDF Archaeology
The low-cost path to AI Mastery
antonyarkov.substack.com·1d·
Discuss: Substack
⚡Proof Automation
SAM-DCE: Addressing Token Uniformity and Semantic Over-Smoothing in Medical Segmentation
arxiv.org·5h
📊Learned Metrics