💻 Local LLMs

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

Customizing text content moderation with Amazon Nova
aws.amazon.com·1d
🏠Self-hosted AI
Neural Networks from Scratch in Python: Simpler Than You Think
hamza.se·19h·
Discuss: Hacker News
🧠Neuromorphic Hardware
Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?
arxiv.org·2d
📱Edge AI
Stress-Testing Model Specs Reveals Character Differences among Language Models
arxiv.org·1d
🎙️Whisper
Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data
arxiv.org·1d
📱Edge AI
Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile Vision-Language Agents
arxiv.org·1d
🤖AI agents
Certifiable Safe RLHF: Fixed-Penalty Constraint Optimization for Safer Language Models
arxiv.org·4d
🎙️Whisper
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
arxiv.org·2d
🏗️AI Infrastructure
Covert Quantum Learning: Privately and Verifiably Learning from Quantum Data
arxiv.org·2d
🔐Decentralized Identity
ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
arxiv.org·1d
🎙️Whisper
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
arxiv.org·1d
🏗️AI Infrastructure
From Documents to Dialogue: A step-by-step RAG Journey
dev.to·1d·
Discuss: DEV
🎙️Whisper
Ensemble Deep Learning and LLM-Assisted Reporting for Automated Skin Lesion Diagnosis
arxiv.org·2d
🏗️AI Infrastructure
Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin
arxiv.org·2d
📱Edge AI
Comparing human and language models sentence processing difficulties on complex structures
arxiv.org·2d
🏗️AI Infrastructure
IASC: Interactive Agentic System for ConLangs
arxiv.org·1d
💬Language Servers
Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
arxiv.org·1d
📱Edge AI
AI Renaissance: Bridging the Gap Between Intuition and Logic
dev.to·1d·
Discuss: DEV
📱Edge AI
Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction
arxiv.org·3d
🧬Computational Biology
10 Data + AI Observations for Fall 2025
towardsdatascience.com·1d
🏗️AI Infrastructure