🗂️ Vector Search

Embedding Similarity, High-dimensional Indexing, Semantic Retrieval, ML Infrastructure

🚀 I Created OctaneDB – The Lightning-Fast Python Vector Database!
dev.to·3h·
Discuss: DEV
🗂️Vector Databases
From Facts & Metrics to Media Machine Learning: Evolving the Data Engineering Function at Netflix
netflixtechblog.com·1d·
Discuss: Hacker News
📊Feed Optimization
Locality-aware Concept Bottleneck Model
arxiv.org·2d
⧗Information Bottleneck
The 10 Best Semantic Search APIs in 2025
shaped.ai·4d
🔍Semantic Search
Ask HN: MCP/API search vs. vector search – what's winning for you?
news.ycombinator.com·3d·
Discuss: Hacker News
🗂️Vector Databases
HHNAS-AM: Hierarchical Hybrid Neural Architecture Search using Adaptive Mutation Policies
arxiv.org·1d
🧠Learned Indexing
V-JEPA 2: Scaling V-JEPA
gonzoml.substack.com·19h·
Discuss: Substack
📊Learned Metrics
Tyson Foods elevates customer search experience with an AI-powered conversational assistant
aws.amazon.com·2d
📡RSS Automation
Show HN: Tabwise – AI data analyst that outperforms ChatGPT and Claude
tabwise.ai·18h·
Discuss: Hacker News
⚡Proof Automation
Show HN: Building a web search engine from scratch (a reply to Wilson Lin)
medium.com·4d·
Discuss: Hacker News
🔍BitFunnel
Improving a similarity search with AI
dev.to·20h·
Discuss: DEV
🔍Semantic Search
Understanding Data Influence with Differential Approximation
arxiv.org·2d
🧠Machine Learning
Adversarial Attacks against Neural Ranking Models via In-Context Learning
arxiv.org·1d
📊Search Ranking
MNIST Data Set (OpenCV
dev.to·1d·
Discuss: DEV
📊Learned Metrics
Stemming -- The Evolution and Current State with a Focus on Bangla
arxiv.org·1d
🔤Morphological Analysis
The AI Building Block You’ve Never Heard Of (But Use Every Day)
hackernoon.com·3d
🔗Parser Combinators
Show HN: Novel GPT-2 sampling and memory architecture
github.com·26m·
Discuss: Hacker News
💎Information Crystallography
D3FNet: A Differential Attention Fusion Network for Fine-Grained Road Structure Extraction in Remote Perception Systems
arxiv.org·1d
🌀Riemannian Computing
Compute Where It Counts: a trainable LLM sparsity enabling 4x CPU speed
crystalai.org·2d·
Discuss: Hacker News
🌊Streaming Algorithms
Deep Dive: OpenAI's GPT-OSS
dev.to·6h·
Discuss: DEV
📊Quantization