Daniel van Strien

ArXiv New ML Datasets - a Hugging Face Space by librarian-bots This tool lets you search arXiv computer‑science papers that are predicted to present new machine‑learning datasets. Enter a keyword or use semantic search, then narrow results by research category...

Semantic search, confidence filtering, updated weekly using Hugging Face Jobs.

Powered by a fine-tuned ModernBERT classifier. Full dataset stored in Lance format on the Hub with vector embeddings.

huggingface.co/spaces/libra...

Datasets and benchmarks drive AI progress, but finding papers that introduce new ones means digging through thousands of arXiv abstracts.

Updated the Dataset Papers on ArXiv app to surface them: 52K+ papers classified as introducing new datasets from 212K CS papers.

IIIF Community Call: IIIF Illustration Detector, Wednesday, February 11 (9am PT / 12pm ET / 5pm UTC

Join us Feburary 11 for a demo of @danielvanstrien.bsky.social's IIIF Illustration Detector.

Zoom on the IIIF Community Calendar: iiif.io/community

image of a index card with a green bounding box prediction around the card contents

Built an object detector from zero-labelled data in one afternoon with help from Claude Code (it can do more than vibe code, TODO apps...)

SAM3 on HF Jobs → correct the errors → train YOLO → repeat.

Three rounds: 31% → 99% accuracy on historical index cards from @natlibscot.bsky.social

davanstrien/archival-index-card-detector · Hugging Face We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Model: huggingface.co/davanstrien/archival-index-card-detector
SAM3 script: huggingface.co/datasets/uv-...

image of a index card with a green bounding box prediction around the card contents

Built an object detector from zero-labelled data in one afternoon with help from Claude Code (it can do more than vibe code, TODO apps...)

SAM3 on HF Jobs → correct the errors → train YOLO → repeat.

Three rounds: 31% → 99% accuracy on historical index cards from @natlibscot.bsky.social

SCIENTISTS QUARREL OVER MARTIAN WOMEN One Says Ladies Have Two Thumbs and X-Ray Eyes ANOTHER SAYS BIG EARS --The Commercial Appeal, 22 Oct 1928

We used to do real science

Thanks! Could be cool to do a few more transformer.js + IIIF demos!

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code.

I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.

It finds illustrated pages in historical books. No server. No GPU.

cc @glenrobson.bsky.social! Finally got time to play with transformers.js and @iiif.bsky.social!

IIIF Illustration Detector - a Hugging Face Space by small-models-for-glam Find illustrated pages in digitized historical books

Paste any IIIF manifest → model classifies every page locally → see where illustrations appear.

Part of small-models-for-glam: small, efficient models for cultural heritage work.

Not everything needs GPT-4!

Try it: huggingface.co/spaces/small-models-for-glam/iiif-illustration-detector

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code.

I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬.

It finds illustrated pages in historical books. No server. No GPU.

The Gradient of Generative AI Release: Methods and Considerations As increasingly powerful generative AI systems are developed, the release method greatly varies. We propose a framework to assess six levels of access to generative AI systems: fully closed; gradual o...

Thanks! If you haven't read it yet, you might also find arxiv.org/abs/2302.04844 interesting!

Here's alt text for the meme: Alt text: "Flex Tape meme format. Top panel: Phil Swift (labeled 'Library Systems Vendor') aggressively spraying water representing 'Outdated systems, metadata issues, disjointed search and complex user needs.' Bottom panel: A hand slapping Flex Tape underwater, with the tape labeled 'AI-powered chat interface.'" This captures the joke that vendors are positioning AI chat as a quick fix for deep-seated library infrastructure problems—a bit like slapping tape on a leak rather than fixing the plumbing.

Just posted my slides from the AI4LAM #FF2025 workshop on open source AI for GLAMs.

Probably slides on their own aren't that useful, but they do feature one of my growing collection of libraries-and-AI memes, so there's that danielvanstrien.xyz/slides.html

At the AI4LAM Fantastic Futures conference this week

Happy to chat about @hf.co, open source AI for GLAMs, or why cultural heritage should bet on small, focused models over closed-source giants!

DM or find me at breaks! #AI4LAM #FF2025

SAM3 Detection Browser - a Hugging Face Space by uv-scripts Explore images and their detected objects using the SAM3 model. Enter a dataset ID, select a split, adjust confidence thresholds, and view detailed object detections with bounding boxes.

Explore some results here: huggingface.co/spaces/uv-sc....

Screenshot of a simple app showing bounding boxes for photographs detected in historic newspaper images.

hf jobs uv run \ --flavor a100-large \ -s HF_TOKEN=HF_TOKEN \ https://huggingface.co/datasets/uv-scripts/sam3/raw/main/detect-objects.py \ -- davanstrien/newspapers-with-images-after-photography-big \ davanstrien/newspapers-photo-predictions \ --class-name "photograph" \ --confidence-threshold 0.4

Building datasets to train smaller, task-focused models used to be incredibly time-consuming.

Very excited to see SAM3 massively lower that barrier. Describe the class you want to detect and get annotated datasets automatically!

Try it yourself: huggingface.co/datasets/uv-...!

Very much looking forward to presenting at this tomorrow. I will be making my usual pitch that datasets are the foundational infrastructure for cultural heritage to benefit from and create useful AI models and tools.

Be warned, I did fire up the meme generator for my slides...

Over the last 24 hours, I have finetuned three Qwen3-VL models (2B, 4B, and 8B) on the CATmuS dataset on @hf.co . The first version of the models are now available on the Small Models for GLAM organization with @danielvanstrien.bsky.social (Links below) Working on improving them further.

Nanonets-OCR2-3B - a Hugging Face Space by akhaliq Discover amazing ML apps made by the community

demo app here: huggingface.co/spaces/akhal...

screenshot of latex output

huggingface.co/nanonets/Nan... might be worth a try for this. Can extract formulas into LaTeX

hf jobs uv run --flavor a100-large --timeout 2h \ -s HF_TOKEN \ https://huggingface.co/datasets/uv-scripts/ocr/raw/main/deepseek-ocr-vllm.py \ NationalLibraryOfScotland/Britain-and-UK-Handbooks-Dataset \ davanstrien/handbooks-deep-ocr \ --resolution-mode base \ --batch-size 2048 \ --prompt-mode free

The command (using @hf.co Jobs - serverless GPU compute)

Full script at huggingface.co/datasets/uv-...

Logs showing ocr progress

DeepSeek-OCR just got vLLM support 🚀

Currently processing @natlibscot.bsky.social's 27,915-page handbook collection with one command.

Processing at ~350 images/sec on A100

Using @hf.co Jobs + uv - zero setup batch OCR!

Will share final time + cost when done!

🤗 Sentence Transformers is joining @hf.co! 🤗

This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face. I'm super excited about the transfer!

Details in 🧵

Supercharge your OCR Pipelines with Open Models We’re on a journey to advance and democratize artificial intelligence through open source and open science.

OCR is one of AI's oldest challenges (first systems: early 1900s!)

Modern vision-language models have transformed what's possible: handwriting, 100+ languages, math formulas, tables, signature extraction...

New @hf.co guide on OCR

huggingface.co/blog/ocr-ope...

Anyone who says OCR is a solved problem has not worked with historic digitised newspapers!

Small models work great for GLAM but there aren't enough examples!

With @wjbmattingly.bsky.social I'm launching small-models-for-glam on @hf.co to create/curate models that run on modest hardware and address GLAM use cases.

Follow the org to keep up-to-date!
huggingface.co/small-models...

Very nice work! IMO, this is the kind of topic that more libraries/GLAM/DH people should be working on. The training of these models is *relatively* simple. As always, the missing ingredient is readily accessible data.

It's been brewing for months: @inriaparisnlp.bsky.social releases CoMMA (Corpus of Multilingual Medieval Archives) !

📚 2.5bn tokens of mostly Latin and French texts
🕰️ 800→1600 CE
📜 23k manuscripts
🖥️ 18k on the reading interface: comma.inria.fr
🔍 Paper: inria.hal.science/hal-05299220v1

(1/🧵)