📄 Text Chunking

Semantic Segmentation, Context Windows, Document Boundaries, Retrieval Units

Vectorless: open-source PDF chatbot without RAG
news.ycombinator.com·1d·
Discuss: Hacker News
🎙️Whisper
Best Vibe Coding Tools in 2025
observer.bearblog.dev·4h·
Discuss: Hacker News
📏Code Metrics
Does GPT-2 Know Your Phone Number? (2020)
bair.berkeley.edu·1d·
Discuss: Hacker News
💻Local LLMs
What's the strongest AI model you can train on a laptop in five minutes?
seangoedecke.com·19h·
Discuss: Hacker News
🧠Intelligence Compression
Why your brain is the biggest bottleneck in AI productivity
jennywanger.com·7h·
Discuss: Hacker News
⚡Proof Automation
LFM2-VL: Efficient Vision-Language Models
liquid.ai·34m·
Discuss: Hacker News
💻Local LLMs
Hyperdimensional Semantic Graph Analysis for Automated Scientific Knowledge Graph Construction
dev.to·2d·
Discuss: DEV
📋Document Grammar
SAEMark: Multi-bit LLM Watermarking with Inference-Time Scaling
arxiv.org·15h
⚙️Compression Benchmarking
RSVLM-QA: A Benchmark Dataset for Remote Sensing Vision Language Model-based Question Answering
arxiv.org·15h
🗂️Vector Search
Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model
arxiv.org·15h
🔍Information Retrieval
Queen Bees: The Resurgence of CMS Repositories in the Age of AI
deanebarker.net·23h·
Discuss: Hacker News
🔌Archive APIs
Text Embedded Swin-UMamba for DeepLesion Segmentation
arxiv.org·1d
🔤Character Classification
InsightStream: AI-Powered Real-Time Content Intelligence Platform
dev.to·1d·
Discuss: DEV
🌊Streaming Systems
Automated Texture Characterization & Predictive Failure Analysis in Compression Testing via Multi-Modal Neural Networks
dev.to·6h·
Discuss: DEV
🧠Machine Learning
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
arxiv.org·15h
🧠Intelligence Compression
Building with Generative AI: Lessons from 5 Projects Part 1: RAG
dev.to·4d·
Discuss: DEV
🤖Grammar Induction
Assessing LLM Text Detection in Educational Contexts: Does Human Contribution Affect Detection?
arxiv.org·15h
💻Local LLMs
Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection
arxiv.org·15h
🔤Character Classification
Self-attention mechanism explained
jtlicardo.com·2d·
Discuss: Hacker News
🚀SIMD Text Processing
Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsampling
arxiv.org·15h
🤖Advanced OCR