| | Benchmarking LLMs/VLMs on document parsing, extraction, VQA (nanonets.com) |
| 1 point by vitaelabitur 2 days ago | past | discuss |
|
| | AI agent hacks McKinsey: five situations when you should not deploy agents (nanonets.com) |
| 4 points by Terretta 7 days ago | past | discuss |
|
| | We Ran 16 AI Models on 9k Real Documents. Here's What We Found (nanonets.com) |
| 3 points by shrishdwi 11 days ago | past | discuss |
|
| | Are ads the only way to scale AI to mainstream users? (nanonets.com) |
| 1 point by nobsagents 39 days ago | past |
|
| | LLM Structured Outputs Handbook (nanonets.com) |
| 377 points by vitaelabitur 66 days ago | past | 64 comments |
|
| | Evaluating OCR-to-Markdown systems is fundamentally broken (nanonets.com) |
| 1 point by PixelPanda 66 days ago | past |
|
| | Show HN: DocStrange: An LLM-Ready Data Platform That Performs Better Than Gemini (nanonets.com) |
| 5 points by souvik3333 5 months ago | past | 5 comments |
|
| | DocStrange – A Python library for LLM-ready data with a new 7B parameter model (nanonets.com) |
| 5 points by zissou11 6 months ago | past |
|
| | Show HN: Open-source 3B param model better than Mistral OCR (nanonets.com) |
| 9 points by PixelPanda 9 months ago | past |
|
| | OCR with Semantic Understanding (nanonets.com) |
| 2 points by prats226 9 months ago | past |
|
| | Benchmarking LLMs on Document Automation (nanonets.com) |
| 2 points by sarthakjain on March 13, 2025 | past |
|
| | Show HN: OCR Benchmark Focusing on Automation (nanonets.com) |
| 58 points by prats226 on March 12, 2025 | past | 21 comments |
|
| | Building an OCR Engine for Windings (nanonets.com) |
| 2 points by PixelPanda on Nov 25, 2024 | past |
|
| | How to tell if your LLM is hallucinating (nanonets.com) |
| 2 points by spikyspider on Oct 23, 2024 | past |
|
| | Fine-Tuning VLMs for Data Extraction (nanonets.com) |
| 6 points by OceanBreez on Oct 4, 2024 | past | 2 comments |
|
| | Table Extraction Using LLMs (nanonets.com) |
| 18 points by StarrySkies11 on Sept 23, 2024 | past | 1 comment |
|
| | Bridging Images and Text – A Survey of VLMs (nanonets.com) |
| 4 points by OceanBreez on Sept 18, 2024 | past |
|
| | Bridging Images and Text – A Survey of VLMs (nanonets.com) |
| 9 points by StarrySkies11 on Sept 17, 2024 | past | 2 comments |
|
| | LLM APIs for Document Data Extraction (nanonets.com) |
| 6 points by prithiv10 on Aug 27, 2024 | past | 3 comments |
|
| | AI vs. AE: lead qualification using LLMs (nanonets.com) |
| 6 points by sarthakjain on Dec 7, 2023 | past |
|
| | Deep learning behind document processing (nanonets.com) |
| 49 points by prats226 on March 8, 2022 | past |
|
| | The unreasonable effectiveness of language models in document processing (nanonets.com) |
| 4 points by prats226 on Feb 24, 2022 | past |
|
| | The unreasonable effectiveness of language models in document processing (nanonets.com) |
| 16 points by prats226 on Feb 8, 2022 | past |
|
| | How does document processing work with multiple languages? (nanonets.com) |
| 5 points by prats226 on Feb 5, 2022 | past |
|
| | How to Make Deep Learning Models That Don’t Suck (2019) (nanonets.com) |
| 3 points by optimalsolver on Feb 17, 2021 | past |
|
| | How to Extract Key-Value Pairs from Documents Using Deep Learning (nanonets.com) |
| 1 point by arunpgandhi on Nov 18, 2020 | past |
|
| | How to extract structured data from invoices (nanonets.com) |
| 2 points by lukastyrychtr on Oct 22, 2020 | past |
|
| | How to build a form reader from scratch using deep learning (nanonets.com) |
| 4 points by arunpgandhi on Oct 13, 2020 | past |
|
| | How to extract structured text from Payslips using deep learning (nanonets.com) |
| 1 point by arunpgandhi on Oct 1, 2020 | past |
|
| | How to extract data from ID cards using deep learning (nanonets.com) |
| 2 points by arunpgandhi on Sept 18, 2020 | past |
|
|
| More |
