💻 Local LLMs

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

AI Teams Contend With Synthetic Data’s Jekyll/Hyde Roles
cacm.acm.org·1d
🔍Vector Forensics
Answer: Best ways to do just-in-time learning. Part 3: getting a teaching summary with NotebookLM
searchresearch1.blogspot.com·13h·
Discuss: searchresearch1.blogspot.com
🤖Automated Parsing
Compress Vectors by 4x by using 8-bit Rotational Quantization
weaviate.io·3h·
Discuss: Hacker News
📊Vector Quantization
Sotasearch.ai – privacy-first research assistant (100% local)
sotasearch.ai·1d·
Discuss: Hacker News
🤖Archive Automation
Paying attention to feature distribution alignment (pun intended)
alexshtf.github.io·3d·
Discuss: Hacker News
📐Linear Algebra
Building your own CLI Coding Agent with Pydantic-AI
martinfowler.com·22h
⚡Proof Automation
LLM Monitoring and Observability: Hands-on with Langfuse
towardsdatascience.com·2d
👁️System Observability
Bridging Foundation Models and Efficient Architectures: A Modular Brain Imaging Framework with Local Masking and Pretrained Representation Learning
arxiv.org·2d
📊Learned Metrics
Aggregate Fictitious Play for Learning in Anonymous Polymatrix Games (Extended Version)
arxiv.org·6h
🔲Cellular Automata
OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
arxiv.org·6h
🏺Computational Archaeology
Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets
arxiv.org·1d
🤝Consensus Protocols
Synthetic Image Detection via Spectral Gaps of QC-RBIM Nishimori Bethe-Hessian Operators
arxiv.org·6h
🌀Fractal Compression
FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter
arxiv.org·6h
✅Verification Codecs
STRATA-TS: Selective Knowledge Transfer for Urban Time Series Forecasting with Retrieval-Guided Reasoning
arxiv.org·1d
🧠Machine Learning
Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?
arxiv.org·1d
🌀Differential Geometry
Language Models Coupled with Metacognition Can Outperform Reasoning Models
arxiv.org·2d
🧠Intelligence Compression
MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use
arxiv.org·1d
✨Algebraic Effects
Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention
arxiv.org·6h
✨Effect Handlers
How Retrieval Algorithms Shape Better LLM Responses?
dev.to·2d·
Discuss: DEV
🔍Information Retrieval
Programmable k-local Ising Machines and all-optical Kolmogorov-Arnold Networks on Photonic Platforms
arxiv.org·2d
🕸️Tensor Networks