Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Unlimited OCR: One-shot long-horizon parsing

github.com

Post reply on HN
Print view View original

101–110 of 119 posts

Re: Unlimited OCR: One-shot long-horizon parsing

#101

Post by SirYandi »

arboles wrote: post #98

I'm going to sound like I live under a rock, but what is the true reason companies open-source genuinely good software? Shouldn't Baidu (or Google) hoard it for themselves to extract the value in a way the competition isn't be able to imitate?

Some people working in big companies believe in the ideals of open source and convince their employers to allow open sourcing a project.

Employers get prestige (useful for the hiring funnel) and sometimes strategically disrupt competitors (e.g. Meta releasing Ollama)

Re: Unlimited OCR: One-shot long-horizon parsing

#102

Post by messe »

pbhjpbhj wrote: post #95
messe wrote: post #68

Earlier quoted context omitted.

> Eire A nitpick, because it's often a dogwhistle: but almost nobody in Ireland calls it that when speaking English. And that's still incorrect in Irish, the correct spelling is Éire.

By saying it's a dogwhistle are you saying that not adding the correct diacritics is considered racist by Irish people? If I change the rest of the sentence to Na Gaeilge will that be better.

No, I'm saying that it's associated with a certain outdated and bigoted attitude toward the Irish.

Using Éire in English, would be seen as odd. You wouldn't say Deutschland or Danmark.

> If I change the rest of the sentence to Na Gaeilge will that be better.

No. And you've used the genitive instead of nominative there, so I have some doubts that you could.

Re: Unlimited OCR: One-shot long-horizon parsing

#103

Post by ranger_danger »

robotswantdata wrote: post #5

Very interesting. The way I understand this works is that the researchers found a clever architectural hack to stop AI from hoarding memory when reading long documents. Normally, when an AI transcribes a 100 page PDF, it tries to remember every single word it has already ingested. This short-term memory (the KV cache) grows linearly O(N) until the model runs out of VRAM and crashes (or caps it) To avoid this, develop…

I thought all the major LLM tools already supported sliding window attention?

Re: Unlimited OCR: One-shot long-horizon parsing

#104

Post by jerrygenser »

arboles wrote: post #98

I'm going to sound like I live under a rock, but what is the true reason companies open-source genuinely good software? Shouldn't Baidu (or Google) hoard it for themselves to extract the value in a way the competition isn't be able to imitate?

Releasing open source models can drive revenue away from them US AI LABS. This can help china win by depriving those labs of revenue for further investment in winning the long term race.

Re: Unlimited OCR: One-shot long-horizon parsing

#105

Post by jeena »

_puk wrote: post #48
robotswantdata wrote: post #5

Very interesting. The way I understand this works is that the researchers found a clever architectural hack to stop AI from hoarding memory when reading long documents. Normally, when an AI transcribes a 100 page PDF, it tries to remember every single word it has already ingested. This short-term memory (the KV cache) grows linearly O(N) until the model runs out of VRAM and crashes (or caps it) To avoid this, develop…

This hits a sweet spot I think for conversations too. I've been playing (for quite a while) on trying to encapsulate long running conversations. You have the overriding context, facts that don't change very often at all. The participants names, their backgrounds etc. Then you have some very fine grained facts (what they ate for breakfast this morning) which might be useful right now, but are irrelevant outside of a g…

I tried to do that for very long translations, I had a sliding window, I had a memory for the important things to keep it consistent, a loop for repairs etc. https://jeena.net/loop-engineering

But for some reason the local models I used back then that was almost 2 years ago) weren't good enough so none of my optimizations did anything good for the translation quality.

Re: Unlimited OCR: One-shot long-horizon parsing

#106

Post by d675 »

ai_fry_ur_brain wrote: post #38
d675 wrote: post #30

Earlier quoted context omitted.

See, leetcode is useful. As I do this leetcode grind, I’ve been why techniques exist / how they’re used irl. Lots of interesting stuff there

Who said it wasnt useful, dont listen to those people.

just the level of questions being asked seems to be high idk, just passed round 1 for big tech. Not feeling great about the rest.

main comment was a bit tongue in cheek

Re: Unlimited OCR: One-shot long-horizon parsing

#107

Post by MattRogish »

ryanisnan wrote: post #94
MattRogish wrote: post #92

Earlier quoted context omitted.

I calculate* the appropriate overlap and the slicer overlaps a certain amount of the previous slice. There is some post-processing assembly required, but it's trivial. [*] SWAG line height, trial and error to figure out the right amount of overlap given LLM error rates, etc.

Interesting. Do you have a uniform data set? E.g. documents of a specific type that you know consistently have similar formats, or is this training something you need to do per-document?

We have some broad shapes - it’s a finite set of “things that are interesting to us” and the dataset is bounded. It’s not “Google Image Search”. But it is kinda like “we have a giant pile of PDFs, pictures, etc and the user wishes to run an arbitrary query on them and extract the information they want. Ex: “I need the to know $something about the data embedded in the corpus, that look like excel data with line charts describing some particular class of metric that are to the left of gray dogs and are about $something_else earlier in the document”

Gemini has a very specific mode where it has been trained on making boxes normalized to a 1000x1000 grid (https://docs.cloud.google.com/gemini-enterprise-agent-platfo...) and in our experience this “just works” AND is very fast on 3.5 and 3.1 models without needing much thinking (so it is not terrifically expensive).

(BTW A+++ gold star triple thumbs up give this person a bonus to whomever did that magic it basically made this task for us tractable. When we first found it nobody else had anything like it - it’s worked so well I haven’t felt any need to look. )

So we say, “Hey Gemini draw box_2d […] around #{things we are interested in}” and then it is pretty easy to then go - ok if this is here and that is there, let’s slice the image in this particular way, making sure to overlap by some amount because the boxes are fuzzy, then send the chunks to a thing that turns it into JSON, then we use something like edge detection to reconstruct the whole from the parts. (Squint and it looks like whole genome shotgun sequencing)

Re: Unlimited OCR: One-shot long-horizon parsing

#109

Post by indiv0 »

mejutoco wrote: post #93
indiv0 wrote: post #55

Earlier quoted context omitted.

> music is basically a greenfield for AI wherever you look AIN'T THAT THE TRUTH. My girlfriend is studying musicology and she has some physical disabilities that make it difficult for her to write things down sometimes. So I try to help her by writing some AI-powered TTS/OCR/etc. apps here and there. It becomes painfully obvious that music was never considered an important part of any AI training dataset, anywhere. T…

> how well Opus 4.8 understands [...] and he'll confidently I always think of the nun character against AI in Mrs Davis: > "Don't give it a name. No one calls Facebook Doug. No one calls Twitter Mary Lou. No one calls them anything, because no one uses them anymore. They use it, and it's not a person. It's code. - Mrs Davis

You're not wrong, but if I'm talking to a Chinese Room, I'm still going to use pronouns and all sorts of meatbag-specific language. It doesn't matter if there really is a real person on the other end or not -- it's easier for me to just default to the assumption that there is. Monkey brain gonna anthropomorphize.

On the other hand if I try to talk to Facebook, all he says in response is "200 OK".

Re: Unlimited OCR: One-shot long-horizon parsing

#110

Post by jbarrow »

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 outputs as a post-processing correction step (https://arxiv.org/abs/2605.24973). Interesting to see the drop-off in quality as you up page count, though.

I also think the attention approach (always attend to the image/prefix, with a sliding window for local context) is neat!

I do wish they updated their comparison table to include more recent work (that scores marginally better on OmniDocBench), like dots.mocr.

Post reply on HN