💻 Local LLMs

Model Quantization, Inference Optimization, GGUF Format, Privacy-preserving AI

AI Thinking, Fast and Slow
danmu.nz·3d·
Discuss: Hacker News
🧮SMT Solvers
Genie 3: A new frontier for world models
deepmind.google·16h·
Discuss: DEV, Hacker News
🏺Computational Archaeology
Using Dspy to Detect Document Boundaries
kmad.ai·3d·
Discuss: Hacker News
📄Document Digitization
PyCharm 2025.2: AI Toolkit for AI Engineers and More!
blog.jetbrains.com·19h
⚡Proof Automation
Everything I Hacked on in 2024
mccormick.cx·15h·
Discuss: Hacker News
🚀Indie Hacking
Let's properly analyze an AI article for once
nibblestew.blogspot.com·6h·
Discuss: Hacker News, nibblestew.blogspot.com
🧠Intelligence Compression
Google opens NotebookLM to younger users
heise.de·21h
🧠Personal Knowledge Base
New Educational App Lets Users Explore the Human Side of AI Alignment
simulateai.io·2d·
Discuss: Hacker News
🔲Cellular Automata
Automating Boundary Filling in Cubical Type Theories
arxiv.org·2d
🔶Cubical Type Theory
TokenSpan: Rethinking Prompt Compression with Aliases and Dictionary Encoding
dev.to·1d·
Discuss: DEV
📝Concrete Syntax
Alignment Monitoring
arxiv.org·2d
⚙️Assembly Verification
Spatial-Frequency Aware for Object Detection in RAW Image
arxiv.org·1d
📊Learned Metrics
HALO: Human Preference Aligned Offline Reward Learning for Robot Navigation
arxiv.org·1d
🔲Cellular Automata
A Methodological Framework for LLM-Based Mining of Software Repositories
arxiv.org·1d
🔗Topological Sorting
Building a Personal AI Info Pipeline: Semantic Monitoring with YAML and GPT
dev.to·12h·
Discuss: DEV
🌀Brotli Internals
On the (In)Significance of Feature Selection in High-Dimensional Datasets
arxiv.org·2h
🧠Machine Learning
Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network
arxiv.org·2h
🌀Hyperbolic Geometry
Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model
arxiv.org·1d
🚀SIMD Text Processing
Learning to Optimize Feedback for One Million Students: Insights from Multi-Armed and Contextual Bandits in Large-Scale Online Tutoring
arxiv.org·2d
📊Feed Optimization
Wukong Framework for Not Safe For Work Detection in Text-to-Image systems
arxiv.org·2d
🤖Advanced OCR