📄 Text Chunking

Semantic Segmentation, Context Windows, Document Boundaries, Retrieval Units

Attackers Season Spam With a Touch of 'Salt'
darkreading.com·3h
📡Feed Security
Can't Recall the Syntax? Try These WYSIWYG Markdown Editors on Linux
itsfoss.com·1d
📟Terminal Typography
Show HN: Blueprintor for Hardware Engineering
zima.run·10h·
Discuss: Hacker News
⚡Homebrew CPUs
State of the Art of AI Tools in Micro-Frontend Architectures • Luca Mezzalira • GOTO 2025
youtube.com·1d
🌀Brotli Internals
A tiny recursive reasoning model achieves 45% on ARC-AGI-1 and 8% on ARC-AGI-2
alexiajm.github.io·4h·
Discuss: Hacker News, Hacker News
🧠Intelligence Compression
Towards a Typology of LLM Chains-of-Thought
1a3orn.com·1d·
Discuss: Hacker News
🌳Context free grammars
AI-Driven Predictive Maintenance of Compression Testing Machines via Multi-Modal Data Fusion & Semantic Parsing
dev.to·1d·
Discuss: DEV
🧠Intelligence Compression
Joint Neural SDF Reconstruction and Semantic Segmentation for CAD Models
arxiv.org·20h
🌀Differential Geometry
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
arxiv.org·20h
🧠Machine Learning
DuPLUS: Dual-Prompt Vision-Language Framework for Universal Medical Image Segmentation and Prognosis
arxiv.org·20h
🤖Advanced OCR
CHORD: Customizing Hybrid-precision On-device Model for Sequential Recommendation with Device-cloud Collaboration
arxiv.org·1d
🎛️Feed Filtering
Detecting Invariant Manifolds in ReLU-Based RNNs
arxiv.org·20h
🌀Riemannian Computing
I built RAGSharp: a lightweight RAG library for .NET
dev.to·1d·
Discuss: DEV
🔌Archive APIs
Multimodal Function Vectors for Spatial Relations
arxiv.org·1d
🧮Vector Embeddings
Detection of retinal diseases using an accelerated reused convolutional network
arxiv.org·20h
🌀Riemannian Computing
Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions
arxiv.org·20h
🧠Machine Learning
Small Language Models for Emergency Departments Decision Support: A Benchmark Study
arxiv.org·20h
🎙️Whisper
Rare Text Semantics Were Always There in Your Diffusion Transformer
arxiv.org·20h
🧮Vector Embeddings
POEM: Explore Unexplored Reliable Samples to Enhance Test-Time Adaptation
arxiv.org·20h
🧮Kolmogorov Complexity
The New Economics of Open Source Data Infrastructure
thenewstack.io·7h
🌊Streaming Databases