Login
Feature Extraction with KNN
(davpinto.github.io) by RicoElectrico | view | 4 comments
Show HN: Ontology-driven knowledge graph extraction from text
by cybermaggedon | view | 0 comments
A theoretical upper limit for offshore wind energy extraction
(cell.com) by Luc | view | 0 comments
PDF-native extraction vs. vision models for document processing
(pymupdf.io) by akaybk | view | 1 comments
Show HN: TrackerNews – Keyword monitoring and insight extraction
(trackernews.app) by winchester6788 | view | 0 comments
Show HN: Extrai – An open-source tool to fight LLM randomness in data extraction
(github.com) by elias_t | view | 0 comments
Agentic Property Extraction: Simple yet Powerful
(aryn.ai) by mehulashah | view | 0 comments
Removal of Ionic Liquid (IL) from Herbal Materials After Extraction
(mdpi.com) by PaulHoule | view | 0 comments
CDox: A Google Docs style editor with no AI training or data extraction
(cdox.ca) by jethronethro | view | 0 comments
High-efficiency atmospheric water harvesting enabled by ultrasonic extraction
(nature.com) by PaulHoule | view | 0 comments
Ask HN: Codex vs. 5.1 for pdf table-to-JSON extraction?
by oliver236 | view | 0 comments
High-efficiency atmospheric water harvesting enabled by ultrasonic extraction
(nature.com) by taubek | view | 1 comments
Insurance Data Extraction with LLMs
(adaptional.com) by acesohc | view | 1 comments
CSS Extraction Library for Vite and Preact
(github.com) by aziis98 | view | 1 comments
Ask HN: Local CJK/Latin entity extraction without shipping a model?
by zphou | view | 0 comments
Show HN: MemReader: From Passive to Active Extraction for Long-Term Agent Memory
(arxiv.org) by MemTensor | view | 0 comments
SoWScanner: AI extraction and deterministic scoring for SOW risk analysis
(sowscanner.com) by noisysilence | view | 1 comments
Show HN: Writers Studio – macOS writing app with AI entity extraction
(litestep.com) by xclusive36 | view | 0 comments
GLiNER2: Unified Schema-Based Information Extraction
(github.com) by apwheele | view | 0 comments
Unstract: Open-source platform to ship document extraction APIs/MCPs in minutes
(github.com) by naren87 | view | 0 comments
Serica: Single-binary web search and article extraction in Rust
(github.com) by walkthestars | view | 0 comments
Clean Web-to-Markdown: Fast HTML Extraction for LLMs and RAG
(markdown.usemy.cloud) by petoz | view | 0 comments
Show HN: Automated XBRL Data Extraction for 10ks and 10qs
(xbrlmetrics.com) by Loris_jk | view | 0 comments
Extract Anything from Any PDF: Inside Foxit's Advanced Extraction Engine
(developer-api.foxit.com) by fagnerbrack | view | 0 comments
When Search Eats the Web: A Model of Corpus Erosion Under Generative Extraction
(arxiv.org) by sypsyp | view | 1 comments
Adaptive video frame extraction for SfM, Gaussian Splatting, and photogrammetry
(github.com) by oryx1729 | view | 0 comments
Show HN: EU-hosted content extraction API
(danubia.tech) by gbogard | view | 0 comments
Sitegeist – The ultimate design extraction toolkit
(chromewebstore.google.com) by BillyMangino | view | 0 comments
The Souq: Value Creation and Extraction in OpenRouter
(robvc.com) by pama | view | 0 comments
When Search Eats the Web: A Model of Corpus Erosion Under Generative Extraction
(arxiv.org) by p4bl0 | view | 0 comments
Why PDF extraction for RAG breaks, and one approach to make it verifiable
(github.com) by nattanko | view | 1 comments
Vidoro is a privacy-focused online media toolkit for video compression, audio extraction, and file conversion. It offers simple browser-based tools, local processing where possible, and support for both English and Portuguese users.
(vidoro.io) by 高赫阳 | view
TensorLift: Auto Extraction of ISA Semantics from Accelerator RTL via MLIR
(arxiv.org) by matt_d | view | 0 comments
Local models head to head for extraction
(rakuensoftware.com) by jbailes | view | 0 comments
Grounded document extraction with bounding-box citations
(pspdfkit.github.io) by marakiii | view | 0 comments
Pdf-inspector: Rust lib for PDF inspection, classification, and text extraction
(github.com) by 7777777phil | view | 0 comments
Model extraction of SynthID Watermark Detector and exploring adversarial attacks
(fyx.me) by Retr0id | view | 0 comments
Fast Rust Library for PDF text extraction
(github.com) by abrbhat | view | 0 comments
Xberg 1.0 released: document extraction for a world of tooling
(bytecode.news) by jottinger | view | 0 comments
GrapheneOS protections against data extraction from locked devices
(discuss.grapheneos.org) by Cider9986 | view | 0 comments
Show HN: Fitter – declarative web-data extraction,running in the browser also
(pxyup.github.io) by pyxru | view | 0 comments
Show HN: CockroachCrawler–1 package for crawling,browsers,PDF,extraction,and MCP
(github.com) by Cognifyr | view | 0 comments
Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
(arxiv.org) by ankitg12 | view | 0 comments
Making LLM extraction trustworthy enough to act on
(zakihsn.com) by zakihasan | view | 0 comments
Extraction POC works on 10 documents and breaks on 10k
(mwylot.net) by martin_martin | view | 0 comments
A 2-in-1 OSINT suite for deep email and username metadata extraction
(github.com) by json-hunter07 | view | 0 comments
High-integrity HTML extraction for AI agents (with native MCP)
(github.com) by MerlijnW70 | view | 0 comments
Physicists recreate black hole energy extraction in the lab
(sciencedaily.com) by stonlyb | view | 0 comments
Are LLMs good enough for Document Extraction?
(unsiloed.ai) by ritzaco | view | 0 comments
Show HN: Refloow Geo Forensics 1.4 – Local EXIF extraction and timeline mapping
(github.com) by refloow | view | 0 comments