💻 Local LLMs

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

Song recommendations with F# free monads
blog.ploeh.dk·1d
🔗Functional Compilers
k-NN Classification and Model Evaluation
dev.to·8h·
Discuss: DEV
🧠Machine Learning
Language Models Coupled with Metacognition Can Outperform Reasoning Models
arxiv.org·11h
🧠Intelligence Compression
Show HN: yolo-cls – C++ batch image classification CLI with ONNX Runtime
github.com·2d·
Discuss: Hacker News
🔤Character Classification
FedKLPR: Personalized Federated Learning for Person Re-Identification with Adaptive Pruning
arxiv.org·11h
🧠Machine Learning
Programmable k-local Ising Machines and all-optical Kolmogorov-Arnold Networks on Photonic Platforms
arxiv.org·11h
🕸️Tensor Networks
PGF-Net: A Progressive Gated-Fusion Framework for Efficient Multimodal Sentiment Analysis
arxiv.org·1d
📝ABNF Parsing
HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation
arxiv.org·11h
🎯Content Recommendation
SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
arxiv.org·11h
🔗Monadic Parsing
MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs
arxiv.org·11h
🧮Kolmogorov Complexity
MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
arxiv.org·4d
🔐Homomorphic Encryption
A Novel Framework for Uncertainty Quantification via Proper Scores for Classification and Beyond
arxiv.org·11h
📊Learned Metrics
Try My ~3.5 Million Parameters Model Instead for ✨😉
dev.to·1d·
Discuss: DEV
📝Text Parsing
LLM Assertiveness can be Mechanistically Decomposed into Emotional and Logical Components
arxiv.org·11h
🧠Intelligence Compression
HiCL: Hippocampal-Inspired Continual Learning
arxiv.org·11h
🔲Cellular Automata
Scalable ML Deployments Made Simple with KitOps and Kubernetes (No Hardware Required)
dev.to·1h·
Discuss: DEV
🔄Reproducible Builds
Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
arxiv.org·1d
🧠Machine Learning
Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages
arxiv.org·11h
💻Programming languages
How to Benchmark Classical Machine Learning Workloads on Google Cloud
towardsdatascience.com·18h
⚡Performance Mythology
Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Models
arxiv.org·11h
🌍Cultural Algorithms