🧠 Learned Indexes

ML-assisted Data Structures, Neural Networks, B-tree Replacement, Database Optimization

GoMem is a high-performance memory allocator library for Go
github.com·1d
🧠Memory Allocators
I played 1k hands of online poker and built a web app with Cursor AI
blog.rchase.com·2d·
Discuss: Hacker News
🚀Indie Hacking
Can AI Co-Design Distributed Systems? Scaling from 1 GPU to 1k
harvard-edge.github.io·10h·
Discuss: Hacker News
🎯Performance Proofs
LoRA Explained: Faster, More Efficient Fine-Tuning with Docker
docker.com·1d
💻Local LLMs
Self-Improving LLM Agents at Test-Time
arxiv.org·1d
🧠Intelligence Compression
When AI Learns to Think
dev.to·1d·
Discuss: DEV
🔲Cellular Automata
From Keywords to Clusters: AI-Driven Analysis of YouTube Comments to Reveal Election Issue Salience in 2024
arxiv.org·1d
📊Feed Optimization
SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks
arxiv.org·1d
🧠Neural Codecs
GNN Predictions: Hidden Bugs and the Verification Nightmare by Arvind Sundararajan
dev.to·10h·
Discuss: DEV
⚙️Proof Engineering
Statistical Analysis Using NumPy and SciPy: A Practical Guide
dev.to·3d·
Discuss: DEV
📐Linear Algebra
Enhancing Vector Signal Generator Accuracy with Adaptive Polynomial Regression Calibration
dev.to·19h·
Discuss: DEV
📡Audio Modulation
BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data
arxiv.org·3d
🧠Machine Learning
Spectral Graph Clustering under Differential Privacy: Balancing Privacy, Accuracy, and Efficiency
arxiv.org·2d
📈Spectral Graph Theory
Can Risk-taking AI-Assistants suitably represent entities
arxiv.org·1d
🔗Constraint Handling
CaRT: Teaching LLM Agents to Know When They Know Enough
arxiv.org·1d
🔲Cellular Automata
Krish Naik: Complete RAG Crash Course With Langchain In 2 Hours
dev.to·10h·
Discuss: DEV
📊Multi-vector RAG
Exponential Error Bounds for Information Bottleneck Source Coding Problems
arxiv.org·1d
📐Compression Bounds
Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
arxiv.org·1d
🧮Theorem Proving
A small number of samples can poison LLMs of any size
dev.to·1d·
Discuss: DEV
💻Local LLMs
Implicit Models: Expressive Power Scales with Test-Time Compute
arxiv.org·4d
🎯Performance Proofs