Web Analytics Made Easy - Statcounter

Blog

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Read post
Read post

The €825,000 you saved before lunch

The impossible use case - Season 1, episode 01: Procurement

May 13, 2026
Use Cases
Read post
Read post

Deep Research is now Open

Agent-ModernColBERT adds ~10% over Reason-ModernColBERT on BrowseComp-Plus, stays at 149M parameters, and brings GPT-5 + Qwen3-8B-level retrieval performance to a fully open stack.

May 12, 2026
R&D
Read post
Read post

EDiTh: Sharing the Data Nobody Shares

Meet EDiTh: a synthetic enterprise corpus built to benchmark what public datasets can't touch: 1,004 PDFs in six languages and 36 ground-truth use cases.

April 27, 2026
Blog
Read post
Read post

Your RAG Pipeline Is Eating Your Roadmap

The production gap, the retrieval trap, and the way out.

April 24, 2026
Blog
Read post
Read post

🔴 The Retriever You Actually Need

Introducing LateOn and DenseOn, two Apache 2.0 retrievers: SOTA on BEIR, built to generalize.

April 21, 2026
R&D
Read post
Read post

Document Intelligence at First Sight

OriOn-Qwen-SR1: Fast Implicit Reasoning for Long Documents

April 9, 2026
R&D
Read post
Read post

Open-Source LightOnOCR-2 Just Outscored Claude, GPT-5, Qwen3, Mistral and Mathpix at Table Extraction

The most valuable information in enterprise documents doesn't live in paragraphs. It lives in tables

April 7, 2026
R&D
Read post
Read post

LightOn | News April 2026

Trending Today. In Paradigm Now. Discover LightOn's latest breakthroughs.

April 3, 2026
Blog
Read post
Read post

The Bloated Retriever Era Is Over

Reason-ModernColBERT tops BrowseComp-Plus, the most rigorous agentic search benchmark, across every metric, with 54× fewer parameters and fewer search calls.

March 19, 2026
R&D

No matching results found

We couldn’t find what you searched for. Try different keywords.