191–200 of 252 posts
OCR is not a great name for these models. While they can do traditional OCR such as digitize and scanned PDF for example, they do so much more.
>they do so much more I'm not familiar. What else are they good for?
Earlier quoted context omitted.
Yeah, but handling macOS is a infrastructure-capacity sucks, Apple really doesn't want you to so tooling is almost none existing. I've setup CI/CD stacks before that needed macOS builders and it's always the most cumbersome machines to manage as infrastructure.
AWS literally lets you deploy Macs as EC2 instances, which I believe includes all of AWS's usual EBS storage and disk imaging features.
Earlier quoted context omitted.
AWS literally lets you deploy Macs as EC2 instances, which I believe includes all of AWS's usual EBS storage and disk imaging features.
Alright, so now the easy thing is done, now how do you actually manage them, keep them running and do introspection without resorting to SSH or even remote desktop?
Looks great, but looking at the benchmark, can’t help but think about how crazy good dots-ocr is as a model. Too bad they’re not as open as the Deepseek team because its so crazy good and would love to know how it was trained.
If you look you'd notice that it's the same Haoran Wei behind DeepSeek-OCR and GOT-OCR2.0 :p
Earlier quoted context omitted.
Classical OCR still probably make undesirable su6stıtutìons in CJK from there being far too many of similar ones, even some absurd ones that are only distinguishable under microscope or by looking at binary representations. LLMs are better constrained to valid sequences of characters, and so they would be more accurate. Or at least that kind of thing would motivate them to re-implement OCR with LLM.
Huh... Would it work to have some kind of error checking model that corrected common OCR errors? That seems like it should be relatively easy.
Earlier quoted context omitted.
Huh... Would it work to have some kind of error checking model that corrected common OCR errors? That seems like it should be relatively easy.
It's harder then it first seems. The root problem is that for text like "hallo", correcting to "hello" may be fixing an error or introducing an error. In general, the more aggressive your error correction, the more errors you inadvertently introduce. You can try and make a judgement based on context ("hallo, how are you?"), which certainly helps, but it's only a mitigation. Light error correction is common and effect…
The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote >Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios,…
Text tokens are quantized and represent subword units, vision tokens only exist in the embedding space. The way text tokenization works in LLMs is that you have a "lookup table" of (small) token ids to (large) vector embeddings. To pass text to the LLM, you split it at token boundaries, convert strings to token ids, and then construct the "context", a matrix where each row is a vector taken from that lookup table. Tr…
My impression is that OCR is basically solved at this point. The OmniAI benchmark that's also referenced here wasn't updated with new models since February 2025. I assume that's because general purpose LLMs have gotten better at OCR than their own OCR product. I've been able to solve a broad range of OCR tasks by simply sending each page as an image to Gemini 2.5 Flash Lite and asking it nicely to extract the content…
Here's a result I got https://github.com/simonw/research/blob/main/deepseek-ocr-nv... - against this image: https://static.simonwillison.net/static/2025/ft.jpeg
I figured out how to get this running on the NVIDIA Spark (ARM64, which makes PyTorch a little bit trickier than usual) by running Claude Code as root in a new Docker container and having it figure it out. Notes here: https://simonwillison.net/2025/Oct/20/deepseek-ocr-claude-co... Here's a result I got https://github.com/simonw/research/blob/main/deepseek-ocr-nv... - against this image: https://static.simonwillison.n…
Thanks for running the test quickly!
