Viewing profile — jbarrow

Wrote a paper ( https://arxiv.org/abs/2606.19334 ) on how we collected and built the dataset. Just covers the United States. Happy to answer any questions!

I'm always glad to see more multi-page work in VLM-based OCR. Especially single-pass. One of the few other multi-page papers from recently, MinerU-Popo, treats fixing up multi-page…

Very impressed with how much the Gemma ecosystem has advanced just this week. Gemma 12B, multitoken prediction, and official quants released. Feels like Google is putting real effo…

Very cool to see a company pushing what's possible with (relatively) tiny models! A 350M parameter trained on 28T tokens that, from the benchmarks, is competitive with Qwen3.5-0.8B…

Shared this because I was having fun thinking through floating point numbers the other day. I worked through what fp6 (e3m2) would look like, doing manual additions and multiplicat…

I've been noticing a _lot_ more AI-generated/edited content of late, both comments and stories. It's gotten to the point that I spend a lot less time on HN than I used to, and if i…

Watsi is incredibly inspiring! I’ve been a monthly donor since ~the beginning when I was just an undergraduate, and I still read the stories and emails I receive. I’m glad that you…

The whole thing feels AI written, generated from the codebase.* *this is incorrect per the author’s response, my apologies. For instance, it goes into (nano)vLLM internals and does…

Super interesting. Would you be willing to try the Python package ( https://github.com/jbarrow/commonforms ) or share the PDFs? For the non-ONNX models there are some inference tri…

Hey, Benjamin, thanks for the attribution! Happy to field any questions HN users have. It's really gratifying to see people building on the work, and I love that it's possible to d…

Woah, did not realize that, haha. Let me know if it works well!

Training ML models for PDF forms. You can try out what I’ve got so far with this service that automatically detects where fields should go and makes PDFs fillable: https://detect.s…

Existing “auto-fillable” tools are pretty lackluster in my experience. CommonForms is tooling that can automatically detect form fields in PDFs and turn those PDFs into fillable do…

I’m personally a huge fan of Modal, and have been using their serverless scale-to-zero GPUs for a while. We’ve seen some nice cost reductions from using them, while also being able…

If you enjoyed this essay, you should check out the author’s current project, Dynamicland[1]. It is a wonderful expression of what computing and interaction could be. Even the proj…

Editing text in PDFs is _really_ hard compared to other document formats because most PDFs don't really encode the "physics" of the document. I.e. there isn't a notion of a "text b…

Wonderful! Inserted form-fields show up in Preview and Acrobat, which is not a trivial task. I run a little AI-powered tool that automatically figures out where form fields should …

I'm sorry I missed this earlier, but I absolutely believe that it could do that. Do you have any pointers to PDF forms that work well or don't work well with screen readers? I'd be…

My hobby project is building a form filling assistant for complex forms, but it turns out that not every PDF form is digitally fillable. A lot of PDF forms are still made with the …

> Unfortunately Gemini really seems to struggle on this, and no matter how we tried prompting it, it would generate wildly inaccurate bounding boxes Qwen2.5 VL was trained on a spe…