🚀 Introducing DPT-2 mini (Preview) Lightweight parsing for simple, digital documents. DPT-2 mini is a streamlined model designed for high-volume, cost-efficient workloads where documents are clean, predictable, and digitally generated. If your inputs are simple invoices,

Checkout the Blog:

Native-Language Document Extraction with ADE! Most extraction tools depend on translation pipelines, which introduce loss of meaning, misclassification, and extra steps for teams working with non-English documents. This blog breaks down why this “translation tax” creates

Grow faster on the world's largest group chat.

We’re hosting this week’s ADE Office Hours on Thursday. ⚡ If you're building with ADE, bring your questions and join us for direct guidance from the team. 📅 Thursday, December 4 ⏰ 9:00 AM PT 👉 Register here: https://t.co/yuJcVgnHMD

LoanLens AI is the first prize winner from our Financial AI Hackathon. 🏆 GitHub Repo: https://t.co/2R06oJ8bHH Demo Video:

Multi-agent AI system for Intelligent Loan Processing and Fraud Detection! Loan officers usually spend hours reviewing bank statements, payslips, IDs, tax reports, and credit profiles. The process is slow, inconsistent, and vulnerable to fraud. This project showed how an

Can it really be a coincidence? Smart Investors Hold Gold. Find out more at Goldhub

Black Friday ads are chaotic. ADE turns them into a clean shopping list. Holiday ad booklets are packed with dense layouts, mixed fonts, and cluttered product grids. Great for deals, terrible for quick decisions. We ran a physical Black Friday booklet through LandingAI’s

🦃 16 lbs of Turkey for $9.12? We analyzed the vintage ad. 🗞️🕰️ This Thanksgiving, we pushed a chaotic, grainy 1950s newspaper circular through the LandingAI ADE Playground to see how well it could decode the vintage deals. The scan was messy. Fonts were inconsistent. The

ADE Playground: https://t.co/vMH6VkyQTX ADE Python library:

Lightweight model to parse digital native documents ⚡️ We introduced DPT-2 mini (Preview) last week, our lightweight model built for high volume, predictable, digitally generated documents. If you work with simple invoices, digital contracts, memos, letters, or basic forms,

Trump says NEWSMAX is 'terrific!' Click below to find out why...

👉 Full write up: https://t.co/C45WMvfyog 👉 Reproducible repo: https://t.co/TUwKraUwRC

99.15% DocVQA accuracy without using images in QA 🚀 We ran the DocVQA validation split with Agentic Document Extraction (ADE) using DPT-2 and answered every question using only the parsed output. The result came in at 5,286 correct out of 5,331, which is 99.15% accuracy powered

The Financial AI Hackathon brought serious builder energy. ⚡ More than 290 participants and 50 submissions came together to reimagine financial automation using Agentic Document Extraction(ADE), LLMs and agentic frameworks. Watch the full recap video to see the projects, the

If you work with real documents, you already know OCR misses the details that matter. In our latest webinar, we showed how Agentic Document Extraction (ADE) fixes that gap by reading documents as layouts, tables, figures, forms, and relationships, not just text. Here is what

The coming years will split companies into two groups: those that become AI-native and those left catching up. The innovators who harness AI now will define the winners of tomorrow. Follow me for strategic insights on leading through the AI revolution.

Retail banking looks structured. The documents behind it? Not even close. Loan packets shift layouts. Credit card applications mash tables and checkboxes together. KYC IDs combine photos, seals, stamps, and tiny text. Statements drift and blur across scans. This is the real

We’re kicking off ADE Office Hours. ⚡ If you're working with Agentic Document Extraction (ADE), this is your chance to get direct guidance from the LandingAI team. Bring your questions and challenges. It’s an open, informal hour focused entirely on helping you move faster.

AI Dev 25 in NYC was packed. ⚡ Last Friday was incredible with the community at AI Dev 25. The hallway was buzzing nonstop with builders stopping by to test their documents, talk through real use cases, and dive deep into Agentic Document Extraction (ADE). Yong Park delivered

We’re live at AI Dev 25 by @DeepLearningAI in New York ⚡ Find the LandingAI team at booth 13 and put Agentic Document Extraction (ADE) to the test. Bring your toughest PDFs, forms or statements and try them live with the team. Watch episode 1 of “Will It Extract” to see ADE

Need a job? Join ICE today. ICE offers competitive salaries & benefits like health insurance and retirement plans.

🚀 DPT-2 is now Generally Available! Our latest parsing model for Agentic Document Extraction (ADE) is officially out of preview. DPT-2 delivers stronger table parsing, smarter figure captioning, and more accurate chunk detection, giving developers cleaner and more reliable

If you’ve ever parsed a complex table, you know the pain. Receipts, statements, and reports are packed with dense tables that most parsers and OCR tools can’t handle. Here’s what usually goes wrong: • Headers merge or span rows and get misread • Flattened tables lose