💻 Local LLMs

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

Which AI chatbot is the best at protecting your privacy?
euronews.com·22h
🎛️Feed Filtering
Study reveals how much energy AI uses to answer your questions
mercurynews.com·4h
🧠Intelligence Compression
SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning
arxiv.org·18h
💻Programming languages
CLGRPO: Reasoning Ability Enhancement for Small VLMs
arxiv.org·1d
📏Linear Logic
Fast Rate Information-theoretic Bounds on Generalization Errors
arxiv.org·1d
⧗Information Bottleneck
QueueEDIT: Structural Self-Correction for Sequential Model Editing in LLMs
arxiv.org·1d
🔗Monadic Parsing
Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"
arxiv.org·1d
🌳Context free grammars
Practical tips to optimize documentation for LLMs, AI agents, and chatbots
biel.ai·1d·
Discuss: Hacker News
🤖Archive Automation
MATE: LLM-Powered Multi-Agent Translation Environment for Accessibility Applications
arxiv.org·18h
🎙️Whisper
OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
arxiv.org·1d·
Discuss: Hacker News
🧮Kolmogorov Complexity
Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond
arxiv.org·2d
🧮Kolmogorov Complexity
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
arxiv.org·1d
📝Concrete Syntax
Machine Learning Fundamentals: active learning
dev.to·1d·
Discuss: DEV
🤖Grammar Induction
UltraSketchLLM: Saliency-Driven Sketching for Ultra-Low Bit LLM Compression
arxiv.org·1d
🗜️LZW Variants
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
arxiv.org·1d
📏Linear Logic
🧠 The Illusion of Thinking: Apple’s Deep Dive into AI’s Reasoning Limits
dev.to·6h·
Discuss: DEV
🧠Intelligence Compression
Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge
arxiv.org·18h
🧠Intelligence Compression
Quantum-Classical Hybrid Quantized Neural Network
arxiv.org·1d
📊Quantization
Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
arxiv.org·1d
🌀Brotli Internals
Machine Learning Fundamentals: accuracy with python
dev.to·1d·
Discuss: DEV
👁️Observatory Systems