Embeddings Optimization

Feeds to Scour
SubscribedAll
Scoured 21 posts in 24.2 ms

HNSW vs LSH: How Elasticsearch hits 0.99 recall@10 at 15,000 QPS — and what it costs

 📇Vector Indexing  Content type: Blog
elastic.co·

Understanding HNSW: The Engine Behind Fast Vector Search

 🎯Vector Search
chimchim89.github.io·

ASH: Asymmetric Scalar Hashing With Learned Dimensionality Reduction for High-Fidelity Vector Quantization

 🗜️Vector Compression  Content type: Academic
arxiv.org·

Rayforce

 🎯Qdrant  Content type: Code

HNSW-MS: Hierarchical Graph Indexing Enables Accurate Real-Time Mass Spectral Similarity Search at Repository Scale

 🎯Qdrant  Content type: Academic
biorxiv.org·
Less-relevant results

Postgres 19 Beta 1 is here

 💾Databases
postgresweekly.com·

New comment by yorktanaka2024 in "Ask HN: Who wants to be hired? (June 2026)"

 🔄LLM RAG Pipelines  Content type: Discussion

An ode to self-optimizing query plans

 🔍Percolator

Enterprises Are Quietly Moving Their AI Back On-Premises. Here Is Why.

 🎯Vector Search  Content type: Blog
medium.com·

UniSVQ: 2-bit Unified Scalar-Vector Quantization

 🎯Vector Quantization  Content type: Academic
arxiv.org·

luckyrmp/tinderbox-archive: Personal claude.ai conversation archive: schema, ingest, embeddings, hybrid retrieval, MCP server

 🔌Claude Plugins  Content type: Code
github.com··Hacker News

I wondered how big platforms detect stolen images. So I built the whole system myself.

 🎯Vector Search  Content type: Code

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

 🎯Vector Quantization  Content type: Academic
arxiv.org·

Elasticsearch simdvec deep-dive: Walking the memory tightrope to 2x better vector throughput

 🏗️Search Infrastructure  Content type: Blog
elastic.co·

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

 🎯Colbert  Content type: Academic
arxiv.org·

GoodQ02/goodq4all: Local-first multimodal epistemic memory for scene-level video, audio, and text intelligence.

 🎯Vector Search  Content type: Code
github.com··Hacker News

MoQ GGUFs and GSQ: Low-Bit GGUFs Are About to Get Much Better

 🆕New AI  Content type: News  Content type: Blog

Aperon Technical Report: Hierarchical No-Pointer Tangent-Local Search for High-Dimensional Approximate Nearest Neighbors

 🎯Vector Search  Content type: Academic
arxiv.org·

wallidsaydi-creator/hom-local: HOM Local — open-source local-first AI memory kernel

 🗂️Vector Indexes  Content type: Code
github.com··Hacker News

BioVid: Autoregressive Video Generation with Biological Behavior Semantic Comprehension

 🗜️Vector Compression  Content type: Academic
arxiv.org·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
Preview post
v

Post Actions

Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s

Recommendations

Add interest / feed
Enter
Not interested
x

Go to

Home
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help